U-Net based algorithms, due to their complex computations, include limitations when they are used in clinical devices. In this paper, we addressed this problem through a novel U-Net based architecture that called fast and accurate U-Net for medical image segmentation task. The proposed fast and accurate U-Net model contains four tuned 2D-convolutional, 2D-transposed convolutional, and batch normalization layers as its main layers. There are four blocks in the encoder-decoder path. The results of our proposed architecture were evaluated using a prepared dataset for head circumference and abdominal circumference segmentation tasks, and a public dataset (HC18-Grand challenge dataset) for fetal head circumference measurement. The proposed fast network significantly improved the processing time in comparison with U-Net, dilated U-Net, R2U-Net, attention U-Net, and MFP U-Net. It took 0.47 seconds for segmenting a fetal abdominal image. In addition, over the prepared dataset using the proposed accurate model, Dice and Jaccard coefficients were 97.62% and 95.43% for fetal head segmentation, 95.07%, and 91.99% for fetal abdominal segmentation. Moreover, we have obtained the Dice and Jaccard coefficients of 97.45% and 95.00% using the public HC18-Grand challenge dataset. Based on the obtained results, we have concluded that a fine-tuned and a simple well-structured model used in clinical devices can outperform complex models.
Frequency domain analysis of radio frequency signal is performed to differentiate between different tissue categories in terms of spectral parameters. However, due to complex relationship between the absorber size and spectral parameters, they cannot be used for quantitative tissue characterization. In an earlier study, we showed that using linear relationship between absorber size and two new spectral parameters namely number of lobes and average lobe width, absorber size can be successfully recovered from photoacoustic signal generated by single absorber. As actual biological tissue contains multiple absorbers, in this study we extended the application of these two new spectral parameters for computing absorber size from signals generated by multiple PA absorbers. We revisited our analytical model to establish two new linear relationships between the absorber radius and number of lobes as well as average lobe width considering multiple absorbers with bandlimited acquisition. A simulation study was performed to validate these linear relationships. A retrospective ex vivo study, in which the spectral parameters were computed using multiwavelength photoacoustic signals, was performed with freshly exercised thyroid specimens from 38 actual human patients undergoing thyroidectomy after having a diagnosis of suspected thyroid lesions. From statistical analysis it is shown that both the parameters were significantly different between malignant and non-malignant thyroid and malignant and normal thyroid tissue. Performance of the supervised classification with the computed spectral parameters showed that the extracted parameters could be successfully used to differentiate malignant thyroid tissue from normal thyroid tissue with reasonable degree of accuracy.
Breast cancer is one of the most fatal diseases leading to the death of several women across the world. But early diagnosis of breast cancer can help to reduce the mortality rate. So an efficient multi-task learning approach is proposed in this work for the automatic segmentation and classification of breast tumors from ultrasound images. The proposed learning approach consists of an encoder, decoder, and bridge blocks for segmentation and a dense branch for the classification of tumors. For efficient classification, multi-scale features from different levels of the network are used. Experimental results show that the proposed approach is able to enhance the accuracy and recall of segmentation by , , and classification by , , respectively than the methods available in the literature.
Although the two dimensional Speckle Tracking Echocardiography has gained a strong position among medical diagnostic techniques in cardiology, it still requires further developments to improve its repeatability and reliability. Few works have attempted to incorporate the left ventricle segmentation results in the process of displacements and strain estimation to improve its performance. We proposed the use of mask information as an additional penalty in the elastic image registration based displacements estimation. This approach was studied using a short axis view synthetic echocardiographic data, segmented using an active contour method. The obtained masks were distorted to a different degree, using different methods to assess the influence of the segmentation quality on the displacements and strain estimation process. The results of displacements and circumferential strain estimations show, that even though the method is dependent on the mask quality, the potential loss in accuracy due to the poor segmentation quality is much lower than the potential accuracy gain in cases where the segmentation performs well.
The purpose of this study was to evaluate an artificial intelligence (AI) system for the classification of axillary lymph nodes on ultrasound compared to radiologists. Ultrasound images of 317 axillary lymph nodes from patients referred for ultrasound guided fine needle aspiration or core needle biopsy and corresponding pathology findings were collected. Lymph nodes were classified into benign and malignant groups with histopathological result serving as the reference. Google Cloud AutoML Vision (Mountain View, CA) was used for AI image classification. Three experienced radiologists also classified the images and gave a level of suspicion score (1-5). To test the accuracy of AI, an external testing dataset of 64 images from 64 independent patients was evaluated by three AI models and the three readers. The diagnostic performance of AI and the humans were then quantified using receiver operating characteristics curves. In the complete set of 317 images, AutoML achieved a sensitivity of 77.1%, positive predictive value (PPV) of 77.1%, and an area under the precision recall curve of 0.78, while the three radiologists showed a sensitivity of 87.8% ± 8.5%, specificity of 50.3% ± 16.4%, PPV of 61.1% ± 5.4%, negative predictive value (NPV) of 84.1% ± 6.6%, and accuracy of 67.7% ± 5.7%. In the three external independent test sets, AI and human readers achieved sensitivity of 74.0% ± 0.14% versus 89.9% ± 0.06% (p = .25), specificity of 64.4% ± 0.11% versus 50.1 ± 0.20% (p = .22), PPV of 68.3% ± 0.04% versus 65.4 ± 0.07% (p = .50), NPV of 72.6% ± 0.11% versus 82.1% ± 0.08% (p = .33), and accuracy of 69.5% ± 0.06% versus 70.1% ± 0.07% (p = .90), respectively. These preliminary results indicate AI has comparable performance to trained radiologists and could be used to predict the presence of metastasis in ultrasound images of axillary lymph nodes.
To compare joint ultrasound measurements between the sexes in healthy volunteers. A cross-sectional study compared the joint ultrasound measurements between the sexes in healthy volunteers. Quantitative (synovial hypertrophy and perpendicular measurement in the largest synovial recess) and semiquantitative (synovial hypertrophy, power Doppler, and bone erosion; score 0-3) ultrasound measurements were performed. Forty-six articular recesses were evaluated and compared between group 1 (100 females) and group 2 (60 males) who were matched by age and BMI. For the quantitative measurements, 7360 recesses were studied. For the semiquantitative measurements, 22,720 recesses were evaluated. Higher values (p < .05) were found in females for the quantitative measurements of synovial hypertrophy for the following: radiocarpal, distal radioulnar and ulnocarpal, second/third dorsal and second/third palmar interphalangeal, second palmar metacarpophalangeal, glenohumeral, hip, talocrural, talonavicular, and talocalcaneal recesses; the highest difference was found for the hip (6.21 ± 1.35 vs. 4.81 ± 2.40) and distal radioulnar (1.46 ± 0.40 vs. 1.07 ± 0.70) recesses. For the semiquantitative measurements, significant differences were found. For synovial hypertrophy, higher measurements for females in the second/third palmar metacarpophalangeal, second palmar proximal interphalangeal, hip, tibiotalar, talonavicular, talocalcaneal, and second metatarsophalangeal recesses (highest difference for second palmar metacarpophalangeal [44 (22.0%) vs. 5 (4.2%)]). For power Doppler, there were higher values for females in the talonavicular recesses and higher values for males in the first/second/fifth metatarsophalangeal recesses (highest difference for fifth [9 (7.5%) vs. 2 (1.0%)]). For bone erosion, there were higher measurements for females in the radiocarpal recesses (10 [5.0%] vs. 0 [0.0%]) and higher values for males in the talonavicular recesses (4 [3.3%] vs. 0 [0.0%]). Higher quantitative and semiquantitative ultrasound measurements of synovial hypertrophy were typically found in females.