Pub Date : 2024-09-30DOI: 10.1007/s10278-024-01281-w
Giovanni Pasini, Alessandro Stefano, Cristina Mantarro, Selene Richiusa, Albert Comelli, Giorgio Ivan Russo, Maria Gabriella Sabini, Sebastiano Cosentino, Massimo Ippolito, Giorgio Russo
The aim of this study is to investigate the role of [18F]-PSMA-1007 PET in differentiating high- and low-risk prostate cancer (PCa) through a robust radiomics ensemble model. This retrospective study included 143 PCa patients who underwent [18F]-PSMA-1007 PET/CT imaging. PCa areas were manually contoured on PET images and 1781 image biomarker standardization initiative (IBSI)-compliant radiomics features were extracted. A 30 times iterated preliminary analysis pipeline, comprising of the least absolute shrinkage and selection operator (LASSO) for feature selection and fivefold cross-validation for model optimization, was adopted to identify the most robust features to dataset variations, select candidate models for ensemble modelling, and optimize hyperparameters. Thirteen subsets of selected features, 11 generated from the preliminary analysis plus two additional subsets, the first based on the combination of robust and fine-tuning features, and the second only on fine-tuning features were used to train the model ensemble. Accuracy, area under curve (AUC), sensitivity, specificity, precision, and f-score values were calculated to provide models' performance. Friedman test, followed by post hoc tests corrected with Dunn-Sidak correction for multiple comparisons, was used to verify if statistically significant differences were found in the different ensemble models over the 30 iterations. The model ensemble trained with the combination of robust and fine-tuning features obtained the highest average accuracy (79.52%), AUC (85.75%), specificity (84.29%), precision (82.85%), and f-score (78.26%). Statistically significant differences (p < 0.05) were found for some performance metrics. These findings support the role of [18F]-PSMA-1007 PET radiomics in improving risk stratification for PCa, by reducing dependence on biopsies.
本研究旨在通过一个强大的放射组学集合模型,研究[18F]-PSMA-1007 PET 在区分高危和低危前列腺癌(PCa)中的作用。这项回顾性研究纳入了143名接受[18F]-PSMA-1007 PET/CT成像的PCa患者。对 PET 图像上的 PCa 区域进行了人工轮廓分析,并提取了 1781 个符合图像生物标记标准化倡议(IBSI)的放射组学特征。该研究采用了迭代 30 次的初步分析管道,包括用于特征选择的最小绝对收缩和选择算子(LASSO)和用于模型优化的五倍交叉验证,以确定对数据集变化最稳健的特征,选择用于集合建模的候选模型,并优化超参数。所选特征的 13 个子集(11 个从初步分析中生成,另外两个子集基于鲁棒特征和微调特征的组合,第二个子集仅基于微调特征)被用于训练模型集合。计算精确度、曲线下面积(AUC)、灵敏度、特异性、精确度和 f-score 值,以提供模型的性能。使用弗里德曼检验(Friedman test)和经邓恩-西达克(Dunn-Sidak)多重比较校正的事后检验(post hoc tests)来验证不同的集合模型在 30 次迭代中是否存在显著的统计学差异。使用鲁棒性特征和微调特征组合训练的模型集合获得了最高的平均准确率(79.52%)、AUC(85.75%)、特异性(84.29%)、精确度(82.85%)和 f 分数(78.26%)。通过减少对活检的依赖,P 18F]-PSMA-1007 PET 放射线组学在改善 PCa 风险分层方面的差异具有统计学意义(p 18F]-PSMA-1007)。
{"title":"A Robust [<sup>18</sup>F]-PSMA-1007 Radiomics Ensemble Model for Prostate Cancer Risk Stratification.","authors":"Giovanni Pasini, Alessandro Stefano, Cristina Mantarro, Selene Richiusa, Albert Comelli, Giorgio Ivan Russo, Maria Gabriella Sabini, Sebastiano Cosentino, Massimo Ippolito, Giorgio Russo","doi":"10.1007/s10278-024-01281-w","DOIUrl":"https://doi.org/10.1007/s10278-024-01281-w","url":null,"abstract":"<p><p>The aim of this study is to investigate the role of [<sup>18</sup>F]-PSMA-1007 PET in differentiating high- and low-risk prostate cancer (PCa) through a robust radiomics ensemble model. This retrospective study included 143 PCa patients who underwent [<sup>18</sup>F]-PSMA-1007 PET/CT imaging. PCa areas were manually contoured on PET images and 1781 image biomarker standardization initiative (IBSI)-compliant radiomics features were extracted. A 30 times iterated preliminary analysis pipeline, comprising of the least absolute shrinkage and selection operator (LASSO) for feature selection and fivefold cross-validation for model optimization, was adopted to identify the most robust features to dataset variations, select candidate models for ensemble modelling, and optimize hyperparameters. Thirteen subsets of selected features, 11 generated from the preliminary analysis plus two additional subsets, the first based on the combination of robust and fine-tuning features, and the second only on fine-tuning features were used to train the model ensemble. Accuracy, area under curve (AUC), sensitivity, specificity, precision, and f-score values were calculated to provide models' performance. Friedman test, followed by post hoc tests corrected with Dunn-Sidak correction for multiple comparisons, was used to verify if statistically significant differences were found in the different ensemble models over the 30 iterations. The model ensemble trained with the combination of robust and fine-tuning features obtained the highest average accuracy (79.52%), AUC (85.75%), specificity (84.29%), precision (82.85%), and f-score (78.26%). Statistically significant differences (p < 0.05) were found for some performance metrics. These findings support the role of [<sup>18</sup>F]-PSMA-1007 PET radiomics in improving risk stratification for PCa, by reducing dependence on biopsies.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142336026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-30DOI: 10.1007/s10278-024-01277-6
Ilker Ozgur Koska, Alper Selver, Fazil Gelal, Muhsin Engin Uluc, Yusuf Kenan Çetinoğlu, Nursel Yurttutan, Mehmet Serindere, Oğuz Dicle
Our primary aim with this study was to build a patient-level classifier for stroke territory in DWI using AI to facilitate fast triage of stroke to a dedicated stroke center. A retrospective collection of DWI images of 271 and 122 consecutive acute ischemic stroke patients from two centers was carried out. Pretrained MobileNetV2 and EfficientNetB0 architectures were used to classify territorial subtypes as middle cerebral artery, posterior circulation, or watershed infarcts along with normal slices. Various input combinations using edge maps, thresholding, and hard attention versions were explored. The effect of augmenting the three-channel inputs of pre-trained models on classification performance was analyzed. ROC analyses and confusion matrix-derived performance metrics of the models were reported. Of the 271 patients included in this study, 151 (55.7%) were male and 120 (44.3%) were female. One hundred twenty-nine patients had MCA (47.6%), 65 patients had posterior circulation (24%), and 77 patients had watershed (28.0%) infarcts for center 1. Of the 122 patients from center 2, 78 (64%) were male and 44 (34%) were female. Fifty-two patients (43%) had MCA, 51 patients had posterior circulation (42%), and 19 (15%) patients had watershed infarcts. The Mobile-Crop model had the best performance with 0.95 accuracy and a 0.91 mean f1 score for slice-wise classification and 0.88 accuracy on external test sets, along with a 0.92 mean AUC. In conclusion, modified pre-trained models may be augmented with the transformation of images to provide a more accurate classification of affected territory by stroke in DWI.
{"title":"Deep Learning Classification of Ischemic Stroke Territory on Diffusion-Weighted MRI: Added Value of Augmenting the Input with Image Transformations.","authors":"Ilker Ozgur Koska, Alper Selver, Fazil Gelal, Muhsin Engin Uluc, Yusuf Kenan Çetinoğlu, Nursel Yurttutan, Mehmet Serindere, Oğuz Dicle","doi":"10.1007/s10278-024-01277-6","DOIUrl":"https://doi.org/10.1007/s10278-024-01277-6","url":null,"abstract":"<p><p>Our primary aim with this study was to build a patient-level classifier for stroke territory in DWI using AI to facilitate fast triage of stroke to a dedicated stroke center. A retrospective collection of DWI images of 271 and 122 consecutive acute ischemic stroke patients from two centers was carried out. Pretrained MobileNetV2 and EfficientNetB0 architectures were used to classify territorial subtypes as middle cerebral artery, posterior circulation, or watershed infarcts along with normal slices. Various input combinations using edge maps, thresholding, and hard attention versions were explored. The effect of augmenting the three-channel inputs of pre-trained models on classification performance was analyzed. ROC analyses and confusion matrix-derived performance metrics of the models were reported. Of the 271 patients included in this study, 151 (55.7%) were male and 120 (44.3%) were female. One hundred twenty-nine patients had MCA (47.6%), 65 patients had posterior circulation (24%), and 77 patients had watershed (28.0%) infarcts for center 1. Of the 122 patients from center 2, 78 (64%) were male and 44 (34%) were female. Fifty-two patients (43%) had MCA, 51 patients had posterior circulation (42%), and 19 (15%) patients had watershed infarcts. The Mobile-Crop model had the best performance with 0.95 accuracy and a 0.91 mean f1 score for slice-wise classification and 0.88 accuracy on external test sets, along with a 0.92 mean AUC. In conclusion, modified pre-trained models may be augmented with the transformation of images to provide a more accurate classification of affected territory by stroke in DWI.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142336031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-26DOI: 10.1007/s10278-024-01137-3
Kubilay Muhammed Sunnetci, Esat Kaba, Fatma Beyazal Celiker, Ahmet Alkan
The differentiation of benign and malignant parotid gland tumors is of major significance as it directly affects the treatment process. In addition, it is also a vital task in terms of early and accurate diagnosis of parotid gland tumors and the determination of treatment planning accordingly. As in other diseases, the differentiation of tumor types involves several challenging, time-consuming, and laborious processes. In the study, Magnetic Resonance (MR) images of 114 patients with parotid gland tumors are used for training and testing purposes by Image Fusion (IF). After the Apparent Diffusion Coefficient (ADC), Contrast-enhanced T1-w (T1C-w), and T2-w sequences are cropped, IF (ADC, T1C-w), IF (ADC, T2-w), IF (T1C-w, T2-w), and IF (ADC, T1C-w, T2-w) datasets are obtained for different combinations of these sequences using a two-dimensional Discrete Wavelet Transform (DWT)-based fusion technique. For each of these four datasets, ResNet18, GoogLeNet, and DenseNet-201 architectures are trained separately, and thus, 12 models are obtained in the study. A Graphical User Interface (GUI) application that contains the most successful of these trained architectures for each data is also designed to support the users. The designed GUI application not only allows the fusing of different sequence images but also predicts whether the label of the fused image is benign or malignant. The results show that the DenseNet-201 models for IF (ADC, T1C-w), IF (ADC, T2-w), and IF (ADC, T1C-w, T2-w) are better than the others, with accuracies of 95.45%, 95.96%, and 92.93%, respectively. It is also noted in the study that the most successful model for IF (T1C-w, T2-w) is ResNet18, and its accuracy is equal to 94.95%.
{"title":"MR Image Fusion-Based Parotid Gland Tumor Detection.","authors":"Kubilay Muhammed Sunnetci, Esat Kaba, Fatma Beyazal Celiker, Ahmet Alkan","doi":"10.1007/s10278-024-01137-3","DOIUrl":"https://doi.org/10.1007/s10278-024-01137-3","url":null,"abstract":"<p><p>The differentiation of benign and malignant parotid gland tumors is of major significance as it directly affects the treatment process. In addition, it is also a vital task in terms of early and accurate diagnosis of parotid gland tumors and the determination of treatment planning accordingly. As in other diseases, the differentiation of tumor types involves several challenging, time-consuming, and laborious processes. In the study, Magnetic Resonance (MR) images of 114 patients with parotid gland tumors are used for training and testing purposes by Image Fusion (IF). After the Apparent Diffusion Coefficient (ADC), Contrast-enhanced T1-w (T1C-w), and T2-w sequences are cropped, IF (ADC, T1C-w), IF (ADC, T2-w), IF (T1C-w, T2-w), and IF (ADC, T1C-w, T2-w) datasets are obtained for different combinations of these sequences using a two-dimensional Discrete Wavelet Transform (DWT)-based fusion technique. For each of these four datasets, ResNet18, GoogLeNet, and DenseNet-201 architectures are trained separately, and thus, 12 models are obtained in the study. A Graphical User Interface (GUI) application that contains the most successful of these trained architectures for each data is also designed to support the users. The designed GUI application not only allows the fusing of different sequence images but also predicts whether the label of the fused image is benign or malignant. The results show that the DenseNet-201 models for IF (ADC, T1C-w), IF (ADC, T2-w), and IF (ADC, T1C-w, T2-w) are better than the others, with accuracies of 95.45%, 95.96%, and 92.93%, respectively. It is also noted in the study that the most successful model for IF (T1C-w, T2-w) is ResNet18, and its accuracy is equal to 94.95%.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142336033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the increasing prevalence of mental illness, accurate clinical diagnosis of mental illness is crucial. Compared with MRI, CT has the advantages of wide application, low price, short scanning time, and high patient cooperation. This study aims to construct a deep learning (DL) model based on CT images to make identification of bipolar disorder (BD) and schizophrenia (SZ). A total of 506 patients (BD = 227, SZ = 279) and 179 healthy controls (HC) was collected from January 2022 to May 2023 at two hospitals, and divided into an internal training set and an internal validation set according to a ratio of 4:1. An additional 65 patients (BD = 35, SZ = 30) and 40 HC were recruited from different hospitals, and served as an external test set. All subjects accepted the conventional brain CT examination. The DenseMD model for identify BD and SZ using multiple instance learning was developed and compared with other classical DL models. The results showed that DenseMD performed excellently with an accuracy of 0.745 in the internal validation set, whereas the accuracy of the ResNet-18, ResNeXt-50, and DenseNet-121model was 0.672, 0.664, and 0.679, respectively. For the external test set, DenseMD again outperformed other models with an accuracy of 0.724; however, the accuracy of the ResNet-18, ResNeXt-50, and DenseNet-121model was 0.657, 0.638, and 0.676, respectively. Therefore, the potential of DL models for identification of BD and SZ based on brain CT images was established, and identification ability of the DenseMD model was better than other classical DL models.
{"title":"Identification of Bipolar Disorder and Schizophrenia Based on Brain CT and Deep Learning Methods.","authors":"Meilin Li, Xingyu Hou, Wanying Yan, Dawei Wang, Ruize Yu, Xixiang Li, Fuyan Li, Jinming Chen, Lingzhen Wei, Jiahao Liu, Huaizhen Wang, Qingshi Zeng","doi":"10.1007/s10278-024-01279-4","DOIUrl":"https://doi.org/10.1007/s10278-024-01279-4","url":null,"abstract":"<p><p>With the increasing prevalence of mental illness, accurate clinical diagnosis of mental illness is crucial. Compared with MRI, CT has the advantages of wide application, low price, short scanning time, and high patient cooperation. This study aims to construct a deep learning (DL) model based on CT images to make identification of bipolar disorder (BD) and schizophrenia (SZ). A total of 506 patients (BD = 227, SZ = 279) and 179 healthy controls (HC) was collected from January 2022 to May 2023 at two hospitals, and divided into an internal training set and an internal validation set according to a ratio of 4:1. An additional 65 patients (BD = 35, SZ = 30) and 40 HC were recruited from different hospitals, and served as an external test set. All subjects accepted the conventional brain CT examination. The DenseMD model for identify BD and SZ using multiple instance learning was developed and compared with other classical DL models. The results showed that DenseMD performed excellently with an accuracy of 0.745 in the internal validation set, whereas the accuracy of the ResNet-18, ResNeXt-50, and DenseNet-121model was 0.672, 0.664, and 0.679, respectively. For the external test set, DenseMD again outperformed other models with an accuracy of 0.724; however, the accuracy of the ResNet-18, ResNeXt-50, and DenseNet-121model was 0.657, 0.638, and 0.676, respectively. Therefore, the potential of DL models for identification of BD and SZ based on brain CT images was established, and identification ability of the DenseMD model was better than other classical DL models.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142336032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Acute leukemia is characterized by the swift proliferation of immature white blood cells (WBC) in the blood and bone marrow. It is categorized into acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML), depending on whether the cell-line origin is lymphoid or myeloid, respectively. Deep learning (DL) and artificial intelligence (AI) are revolutionizing medical sciences by assisting clinicians with rapid illness identification, reducing workload, and enhancing diagnostic accuracy. This paper proposes a DL-based novel BSNEU-net framework to detect acute leukemia. It comprises 4 Union Blocks (UB) and incorporates block feature map distortion (BFMD) with switchable normalization (SN) in each UB. The UB employs union convolution to extract more discriminant features. The BFMD is adapted to acquire more generalized patterns to minimize overfitting, whereas SN layers are appended to improve the model's convergence and generalization capabilities. The uniform utilization of batch normalization across convolution layers is sensitive to the mini-batch dimension changes, which is effectively remedied by incorporating an SN layer. Here, a new dataset comprising 2400 blood smear images of ALL, AML, and healthy cases is proposed, as DL methodologies necessitate a sizeable and well-annotated dataset to combat overfitting issues. Further, a heterogeneous dataset comprising 2700 smear images is created by combining four publicly accessible benchmark datasets of ALL, AML, and healthy cases. The BSNEU-net model achieved excellent performance with 99.37% accuracy on the novel dataset and 99.44% accuracy on the heterogeneous dataset. The comparative analysis signifies the superiority of the proposed methodology with comparing schemes.
{"title":"BSNEU-net: Block Feature Map Distortion and Switchable Normalization-Based Enhanced Union-net for Acute Leukemia Detection on Heterogeneous Dataset.","authors":"Rabul Saikia, Roopam Deka, Anupam Sarma, Salam Shuleenda Devi","doi":"10.1007/s10278-024-01252-1","DOIUrl":"https://doi.org/10.1007/s10278-024-01252-1","url":null,"abstract":"<p><p>Acute leukemia is characterized by the swift proliferation of immature white blood cells (WBC) in the blood and bone marrow. It is categorized into acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML), depending on whether the cell-line origin is lymphoid or myeloid, respectively. Deep learning (DL) and artificial intelligence (AI) are revolutionizing medical sciences by assisting clinicians with rapid illness identification, reducing workload, and enhancing diagnostic accuracy. This paper proposes a DL-based novel BSNEU-net framework to detect acute leukemia. It comprises 4 Union Blocks (UB) and incorporates block feature map distortion (BFMD) with switchable normalization (SN) in each UB. The UB employs union convolution to extract more discriminant features. The BFMD is adapted to acquire more generalized patterns to minimize overfitting, whereas SN layers are appended to improve the model's convergence and generalization capabilities. The uniform utilization of batch normalization across convolution layers is sensitive to the mini-batch dimension changes, which is effectively remedied by incorporating an SN layer. Here, a new dataset comprising 2400 blood smear images of ALL, AML, and healthy cases is proposed, as DL methodologies necessitate a sizeable and well-annotated dataset to combat overfitting issues. Further, a heterogeneous dataset comprising 2700 smear images is created by combining four publicly accessible benchmark datasets of ALL, AML, and healthy cases. The BSNEU-net model achieved excellent performance with 99.37% accuracy on the novel dataset and 99.44% accuracy on the heterogeneous dataset. The comparative analysis signifies the superiority of the proposed methodology with comparing schemes.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142336028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ultrasound-guided quadratus lumborum block (QLB) technology has become a widely used perioperative analgesia method during abdominal and pelvic surgeries. Due to the anatomical complexity and individual variability of the quadratus lumborum muscle (QLM) on ultrasound images, nerve blocks heavily rely on anesthesiologist experience. Therefore, using artificial intelligence (AI) to identify different tissue regions in ultrasound images is crucial. In our study, we retrospectively collected 112 patients (3162 images) and developed a deep learning model named Q-VUM, which is a U-shaped network based on the Visual Geometry Group 16 (VGG16) network. Q-VUM precisely segments various tissues, including the QLM, the external oblique muscle, the internal oblique muscle, the transversus abdominis muscle (collectively referred to as the EIT), and the bones. Furthermore, we evaluated Q-VUM. Our model demonstrated robust performance, achieving mean intersection over union (mIoU), mean pixel accuracy, dice coefficient, and accuracy values of 0.734, 0.829, 0.841, and 0.944, respectively. The IoU, recall, precision, and dice coefficient achieved for the QLM were 0.711, 0.813, 0.850, and 0.831, respectively. Additionally, the Q-VUM predictions showed that 85% of the pixels in the blocked area fell within the actual blocked area. Finally, our model exhibited stronger segmentation performance than did the common deep learning segmentation networks (0.734 vs. 0.720 and 0.720, respectively). In summary, we proposed a model named Q-VUM that can accurately identify the anatomical structure of the quadratus lumborum in real time. This model aids anesthesiologists in precisely locating the nerve block site, thereby reducing potential complications and enhancing the effectiveness of nerve block procedures.
{"title":"Automatic Segmentation of Ultrasound-Guided Quadratus Lumborum Blocks Based on Artificial Intelligence.","authors":"Qiang Wang, Bingxi He, Jie Yu, Bowen Zhang, Jingchao Yang, Jin Liu, Xinwei Ma, Shijing Wei, Shuai Li, Hui Zheng, Zhenchao Tang","doi":"10.1007/s10278-024-01267-8","DOIUrl":"https://doi.org/10.1007/s10278-024-01267-8","url":null,"abstract":"<p><p>Ultrasound-guided quadratus lumborum block (QLB) technology has become a widely used perioperative analgesia method during abdominal and pelvic surgeries. Due to the anatomical complexity and individual variability of the quadratus lumborum muscle (QLM) on ultrasound images, nerve blocks heavily rely on anesthesiologist experience. Therefore, using artificial intelligence (AI) to identify different tissue regions in ultrasound images is crucial. In our study, we retrospectively collected 112 patients (3162 images) and developed a deep learning model named Q-VUM, which is a U-shaped network based on the Visual Geometry Group 16 (VGG16) network. Q-VUM precisely segments various tissues, including the QLM, the external oblique muscle, the internal oblique muscle, the transversus abdominis muscle (collectively referred to as the EIT), and the bones. Furthermore, we evaluated Q-VUM. Our model demonstrated robust performance, achieving mean intersection over union (mIoU), mean pixel accuracy, dice coefficient, and accuracy values of 0.734, 0.829, 0.841, and 0.944, respectively. The IoU, recall, precision, and dice coefficient achieved for the QLM were 0.711, 0.813, 0.850, and 0.831, respectively. Additionally, the Q-VUM predictions showed that 85% of the pixels in the blocked area fell within the actual blocked area. Finally, our model exhibited stronger segmentation performance than did the common deep learning segmentation networks (0.734 vs. 0.720 and 0.720, respectively). In summary, we proposed a model named Q-VUM that can accurately identify the anatomical structure of the quadratus lumborum in real time. This model aids anesthesiologists in precisely locating the nerve block site, thereby reducing potential complications and enhancing the effectiveness of nerve block procedures.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142336027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-25DOI: 10.1007/s10278-024-01274-9
Yvonne Su, Yonatan B Babore, Charles E Kahn
Natural language processing (NLP) is crucial to extract information accurately from unstructured text to provide insights for clinical decision-making, quality improvement, and medical research. This study compared the performance of a rule-based NLP system and a medical-domain transformer-based model to detect negated concepts in radiology reports. Using a corpus of 984 de-identified radiology reports from a large U.S.-based academic health system (1000 consecutive reports, excluding 16 duplicates), the investigators compared the rule-based medspaCy system and the Clinical Assertion and Negation Classification Bidirectional Encoder Representations from Transformers (CAN-BERT) system to detect negated expressions of terms from RadLex, the Unified Medical Language System Metathesaurus, and the Radiology Gamuts Ontology. Power analysis determined a sample size of 382 terms to achieve α = 0.05 and β = 0.8 for McNemar's test; based on an estimate of 15% negated terms, 2800 randomly selected terms were annotated manually as negated or not negated. Precision, recall, and F1 of the two models were compared using McNemar's test. Of the 2800 terms, 387 (13.8%) were negated. For negation detection, medspaCy attained a recall of 0.795, precision of 0.356, and F1 of 0.492. CAN-BERT achieved a recall of 0.785, precision of 0.768, and F1 of 0.777. Although recall was not significantly different, CAN-BERT had significantly better precision (χ2 = 304.64; p < 0.001). The transformer-based CAN-BERT model detected negated terms in radiology reports with high precision and recall; its precision significantly exceeded that of the rule-based medspaCy system. Use of this system will improve data extraction from textual reports to support information retrieval, AI model training, and discovery of causal relationships.
{"title":"A Large Language Model to Detect Negated Expressions in Radiology Reports.","authors":"Yvonne Su, Yonatan B Babore, Charles E Kahn","doi":"10.1007/s10278-024-01274-9","DOIUrl":"https://doi.org/10.1007/s10278-024-01274-9","url":null,"abstract":"<p><p>Natural language processing (NLP) is crucial to extract information accurately from unstructured text to provide insights for clinical decision-making, quality improvement, and medical research. This study compared the performance of a rule-based NLP system and a medical-domain transformer-based model to detect negated concepts in radiology reports. Using a corpus of 984 de-identified radiology reports from a large U.S.-based academic health system (1000 consecutive reports, excluding 16 duplicates), the investigators compared the rule-based medspaCy system and the Clinical Assertion and Negation Classification Bidirectional Encoder Representations from Transformers (CAN-BERT) system to detect negated expressions of terms from RadLex, the Unified Medical Language System Metathesaurus, and the Radiology Gamuts Ontology. Power analysis determined a sample size of 382 terms to achieve α = 0.05 and β = 0.8 for McNemar's test; based on an estimate of 15% negated terms, 2800 randomly selected terms were annotated manually as negated or not negated. Precision, recall, and F1 of the two models were compared using McNemar's test. Of the 2800 terms, 387 (13.8%) were negated. For negation detection, medspaCy attained a recall of 0.795, precision of 0.356, and F1 of 0.492. CAN-BERT achieved a recall of 0.785, precision of 0.768, and F1 of 0.777. Although recall was not significantly different, CAN-BERT had significantly better precision (χ2 = 304.64; p < 0.001). The transformer-based CAN-BERT model detected negated terms in radiology reports with high precision and recall; its precision significantly exceeded that of the rule-based medspaCy system. Use of this system will improve data extraction from textual reports to support information retrieval, AI model training, and discovery of causal relationships.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142336015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-25DOI: 10.1007/s10278-024-01266-9
Yu Huang, Nicholas J Leotta, Lukas Hirsch, Roberto Lo Gullo, Mary Hughes, Jeffrey Reiner, Nicole B Saphier, Kelly S Myers, Babita Panigrahi, Emily Ambinder, Philip Di Carlo, Lars J Grimm, Dorothy Lowell, Sora Yoon, Sujata V Ghate, Lucas C Parra, Elizabeth J Sutton
This work aims to perform a cross-site validation of automated segmentation for breast cancers in MRI and to compare the performance to radiologists. A three-dimensional (3D) U-Net was trained to segment cancers in dynamic contrast-enhanced axial MRIs using a large dataset from Site 1 (n = 15,266; 449 malignant and 14,817 benign). Performance was validated on site-specific test data from this and two additional sites, and common publicly available testing data. Four radiologists from each of the three clinical sites provided two-dimensional (2D) segmentations as ground truth. Segmentation performance did not differ between the network and radiologists on the test data from Sites 1 and 2 or the common public data (median Dice score Site 1, network 0.86 vs. radiologist 0.85, n = 114; Site 2, 0.91 vs. 0.91, n = 50; common: 0.93 vs. 0.90). For Site 3, an affine input layer was fine-tuned using segmentation labels, resulting in comparable performance between the network and radiologist (0.88 vs. 0.89, n = 42). Radiologist performance differed on the common test data, and the network numerically outperformed 11 of the 12 radiologists (median Dice: 0.85-0.94, n = 20). In conclusion, a deep network with a novel supervised harmonization technique matches radiologists' performance in MRI tumor segmentation across clinical sites. We make code and weights publicly available to promote reproducible AI in radiology.
{"title":"Cross-site Validation of AI Segmentation and Harmonization in Breast MRI.","authors":"Yu Huang, Nicholas J Leotta, Lukas Hirsch, Roberto Lo Gullo, Mary Hughes, Jeffrey Reiner, Nicole B Saphier, Kelly S Myers, Babita Panigrahi, Emily Ambinder, Philip Di Carlo, Lars J Grimm, Dorothy Lowell, Sora Yoon, Sujata V Ghate, Lucas C Parra, Elizabeth J Sutton","doi":"10.1007/s10278-024-01266-9","DOIUrl":"https://doi.org/10.1007/s10278-024-01266-9","url":null,"abstract":"<p><p>This work aims to perform a cross-site validation of automated segmentation for breast cancers in MRI and to compare the performance to radiologists. A three-dimensional (3D) U-Net was trained to segment cancers in dynamic contrast-enhanced axial MRIs using a large dataset from Site 1 (n = 15,266; 449 malignant and 14,817 benign). Performance was validated on site-specific test data from this and two additional sites, and common publicly available testing data. Four radiologists from each of the three clinical sites provided two-dimensional (2D) segmentations as ground truth. Segmentation performance did not differ between the network and radiologists on the test data from Sites 1 and 2 or the common public data (median Dice score Site 1, network 0.86 vs. radiologist 0.85, n = 114; Site 2, 0.91 vs. 0.91, n = 50; common: 0.93 vs. 0.90). For Site 3, an affine input layer was fine-tuned using segmentation labels, resulting in comparable performance between the network and radiologist (0.88 vs. 0.89, n = 42). Radiologist performance differed on the common test data, and the network numerically outperformed 11 of the 12 radiologists (median Dice: 0.85-0.94, n = 20). In conclusion, a deep network with a novel supervised harmonization technique matches radiologists' performance in MRI tumor segmentation across clinical sites. We make code and weights publicly available to promote reproducible AI in radiology.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142336029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-23DOI: 10.1007/s10278-024-01276-7
Ni Yao, Hang Hu, Kaicong Chen, Huan Huang, Chen Zhao, Yuan Guo, Boya Li, Jiaofen Nan, Yanting Li, Chuang Han, Fubao Zhu, Weihua Zhou, Li Tian
This study developed and validated a deep learning-based diagnostic model with uncertainty estimation to aid radiologists in the preoperative differentiation of pathological subtypes of renal cell carcinoma (RCC) based on computed tomography (CT) images. Data from 668 consecutive patients with pathologically confirmed RCC were retrospectively collected from Center 1, and the model was trained using fivefold cross-validation to classify RCC subtypes into clear cell RCC (ccRCC), papillary RCC (pRCC), and chromophobe RCC (chRCC). An external validation with 78 patients from Center 2 was conducted to evaluate the performance of the model. In the fivefold cross-validation, the area under the receiver operating characteristic curve (AUC) for the classification of ccRCC, pRCC, and chRCC was 0.868 (95% CI, 0.826-0.923), 0.846 (95% CI, 0.812-0.886), and 0.839 (95% CI, 0.802-0.88), respectively. In the external validation set, the AUCs were 0.856 (95% CI, 0.838-0.882), 0.787 (95% CI, 0.757-0.818), and 0.793 (95% CI, 0.758-0.831) for ccRCC, pRCC, and chRCC, respectively. The model demonstrated robust performance in predicting the pathological subtypes of RCC, while the incorporated uncertainty emphasized the importance of understanding model confidence. The proposed approach, integrated with uncertainty estimation, offers clinicians a dual advantage: accurate RCC subtype predictions complemented by diagnostic confidence metrics, thereby promoting informed decision-making for patients with RCC.
{"title":"A Robust Deep Learning Method with Uncertainty Estimation for the Pathological Classification of Renal Cell Carcinoma Based on CT Images.","authors":"Ni Yao, Hang Hu, Kaicong Chen, Huan Huang, Chen Zhao, Yuan Guo, Boya Li, Jiaofen Nan, Yanting Li, Chuang Han, Fubao Zhu, Weihua Zhou, Li Tian","doi":"10.1007/s10278-024-01276-7","DOIUrl":"https://doi.org/10.1007/s10278-024-01276-7","url":null,"abstract":"<p><p>This study developed and validated a deep learning-based diagnostic model with uncertainty estimation to aid radiologists in the preoperative differentiation of pathological subtypes of renal cell carcinoma (RCC) based on computed tomography (CT) images. Data from 668 consecutive patients with pathologically confirmed RCC were retrospectively collected from Center 1, and the model was trained using fivefold cross-validation to classify RCC subtypes into clear cell RCC (ccRCC), papillary RCC (pRCC), and chromophobe RCC (chRCC). An external validation with 78 patients from Center 2 was conducted to evaluate the performance of the model. In the fivefold cross-validation, the area under the receiver operating characteristic curve (AUC) for the classification of ccRCC, pRCC, and chRCC was 0.868 (95% CI, 0.826-0.923), 0.846 (95% CI, 0.812-0.886), and 0.839 (95% CI, 0.802-0.88), respectively. In the external validation set, the AUCs were 0.856 (95% CI, 0.838-0.882), 0.787 (95% CI, 0.757-0.818), and 0.793 (95% CI, 0.758-0.831) for ccRCC, pRCC, and chRCC, respectively. The model demonstrated robust performance in predicting the pathological subtypes of RCC, while the incorporated uncertainty emphasized the importance of understanding model confidence. The proposed approach, integrated with uncertainty estimation, offers clinicians a dual advantage: accurate RCC subtype predictions complemented by diagnostic confidence metrics, thereby promoting informed decision-making for patients with RCC.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142309616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-23DOI: 10.1007/s10278-024-01244-1
William C Walton, Seung-Jun Kim
Techniques are developed for generating uncertainty estimates for convolutional neural network (CNN)-based methods for registering the locations of lesions between the craniocaudal (CC) and mediolateral oblique (MLO) mammographic X-ray image views. Multi-view lesion correspondence is an important task that clinicians perform for characterizing lesions during routine mammographic exams. Automated registration tools can aid in this task, yet if the tools also provide confidence estimates, they can be of greater value to clinicians, especially in cases involving dense tissue where lesions may be difficult to see. A set of deep ensemble-based techniques, which leverage a negative log-likelihood (NLL)-based cost function, are implemented for estimating uncertainties. The ensemble architectures involve significant modifications to an existing CNN dual-view lesion registration algorithm. Three architectural designs are evaluated, and different ensemble sizes are compared using various performance metrics. The techniques are tested on synthetic X-ray data, real 2D X-ray data, and slices from real 3D X-ray data. The ensembles generate covariance-based uncertainty ellipses that are correlated with registration accuracy, such that the ellipse sizes can give a clinician an indication of confidence in the mapping between the CC and MLO views. The results also show that the ellipse sizes can aid in improving computer-aided detection (CAD) results by matching CC/MLO lesion detects and reducing false alarms from both views, adding to clinical utility. The uncertainty estimation techniques show promise as a means for aiding clinicians in confidently establishing multi-view lesion correspondence, thereby improving diagnostic capability.
本研究开发的技术可为基于卷积神经网络(CNN)的方法生成不确定性估计值,这些方法用于在颅尾(CC)和内外侧斜(MLO)乳腺 X 射线图像视图之间登记病变位置。多视图病灶对应是临床医生在常规乳腺 X 射线检查中确定病灶特征的一项重要任务。自动配准工具可以帮助完成这项任务,但如果这些工具还能提供置信度估计,就能为临床医生带来更大的价值,尤其是在涉及致密组织的病例中,因为在这些病例中病变可能难以被看到。我们利用基于负对数似然(NLL)的成本函数,实施了一套基于深度集合的技术来估计不确定性。这些集合架构涉及对现有 CNN 双视角病变配准算法的重大修改。对三种架构设计进行了评估,并使用各种性能指标对不同的集合规模进行了比较。这些技术在合成 X 光数据、真实 2D X 光数据和真实 3D X 光数据切片上进行了测试。集合生成的基于协方差的不确定性椭圆与配准精度相关,因此椭圆的大小可以为临床医生提供 CC 和 MLO 视图之间映射的可信度指示。研究结果还表明,椭圆的大小可以通过匹配 CC/MLO 病灶检测和减少两个视图的误报来帮助改善计算机辅助检测 (CAD) 结果,从而增加临床实用性。不确定性估计技术有望帮助临床医生自信地建立多视图病变对应关系,从而提高诊断能力。
{"title":"Uncertainty Estimation for Dual View X-ray Mammographic Image Registration Using Deep Ensembles.","authors":"William C Walton, Seung-Jun Kim","doi":"10.1007/s10278-024-01244-1","DOIUrl":"https://doi.org/10.1007/s10278-024-01244-1","url":null,"abstract":"<p><p>Techniques are developed for generating uncertainty estimates for convolutional neural network (CNN)-based methods for registering the locations of lesions between the craniocaudal (CC) and mediolateral oblique (MLO) mammographic X-ray image views. Multi-view lesion correspondence is an important task that clinicians perform for characterizing lesions during routine mammographic exams. Automated registration tools can aid in this task, yet if the tools also provide confidence estimates, they can be of greater value to clinicians, especially in cases involving dense tissue where lesions may be difficult to see. A set of deep ensemble-based techniques, which leverage a negative log-likelihood (NLL)-based cost function, are implemented for estimating uncertainties. The ensemble architectures involve significant modifications to an existing CNN dual-view lesion registration algorithm. Three architectural designs are evaluated, and different ensemble sizes are compared using various performance metrics. The techniques are tested on synthetic X-ray data, real 2D X-ray data, and slices from real 3D X-ray data. The ensembles generate covariance-based uncertainty ellipses that are correlated with registration accuracy, such that the ellipse sizes can give a clinician an indication of confidence in the mapping between the CC and MLO views. The results also show that the ellipse sizes can aid in improving computer-aided detection (CAD) results by matching CC/MLO lesion detects and reducing false alarms from both views, adding to clinical utility. The uncertainty estimation techniques show promise as a means for aiding clinicians in confidently establishing multi-view lesion correspondence, thereby improving diagnostic capability.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142309617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}