One label is all you need: Interpretable AI-enhanced histopathology for oncology.

Artificial Intelligence (AI)-enhanced histopathology presents unprecedented opportunities to benefit oncology through interpretable methods that require only one overall label per hematoxylin and eosin (H&E) slide with no tissue-level annotations. We present a structured review of these methods organized by their degree of verifiability and by commonly recurring application areas in oncological characterization. First, we discuss morphological markers (tumor presence/absence, metastases, subtypes, grades) in which AI-identified regions of interest (ROIs) within whole slide images (WSIs) verifiably overlap with pathologist-identified ROIs. Second, we discuss molecular markers (gene expression, molecular subtyping) that are not verified via H&E but rather based on overlap with positive regions on adjacent tissue. Third, we discuss genetic markers (mutations, mutational burden, microsatellite instability, chromosomal instability) that current technologies cannot verify if AI methods spatially resolve specific genetic alterations. Fourth, we discuss the direct prediction of survival to which AI-identified histopathological features quantitatively correlate but are nonetheless not mechanistically verifiable. Finally, we discuss in detail several opportunities and challenges for these one-label-per-slide methods within oncology. Opportunities include reducing the cost of research and clinical care, reducing the workload of clinicians, personalized medicine, and unlocking the full potential of histopathology through new imaging-based biomarkers. Current challenges include explainability and interpretability, validation via adjacent tissue sections, reproducibility, data availability, computational needs, data requirements, domain adaptability, external validation, dataset imbalances, and finally commercialization and clinical potential. Ultimately, the relative ease and minimum upfront cost with which relevant data can be collected in addition to the plethora of available AI methods for outcome-driven analysis will surmount these current limitations and achieve the innumerable opportunities associated with AI-driven histopathology for the benefit of oncology.

Weakly Supervised MRI Slice-Level Deep Learning Classification of Prostate Cancer Approximates Full Voxel- and Slice-Level Annotation: Effect of Increasing Training Set Size.

BACKGROUND: Weakly supervised learning promises reduced annotation effort while maintaining performance. PURPOSE: To compare weakly supervised training with full slice-wise annotated training of a deep convolutional classification network (CNN) for prostate cancer (PC). STUDY TYPE: Retrospective. SUBJECTS: One thousand four hundred eighty-nine consecutive institutional prostate MRI examinations from men with suspicion for PC (65 ± 8 years) between January 2015 and November 2020 were split into training (N = 794, enriched with 204 PROSTATEx examinations) and test set (N = 695). FIELD STRENGTH/SEQUENCE: 1.5 and 3T, T2-weighted turbo-spin-echo and diffusion-weighted echo-planar imaging. ASSESSMENT: Histopathological ground truth was provided by targeted and extended systematic biopsy. Reference training was performed using slice-level annotation (SLA) and compared to iterative training utilizing patient-level annotations (PLAs) with supervised feedback of CNN estimates into the next training iteration at three incremental training set sizes (N = 200, 500, 998). Model performance was assessed by comparing specificity at fixed sensitivity of 0.97 [254/262] emulating PI-RADS ≥ 3, and 0.88-0.90 [231-236/262] emulating PI-RADS ≥ 4 decisions. STATISTICAL TESTS: Receiver operating characteristic (ROC) and area under the curve (AUC) was compared using DeLong and Obuchowski test. Sensitivity and specificity were compared using McNemar test. Statistical significance threshold was P = 0.05. RESULTS: Test set (N = 695) ROC-AUC performance of SLA (trained with 200/500/998 exams) was 0.75/0.80/0.83, respectively. PLA achieved lower ROC-AUC of 0.64/0.72/0.78. Both increased performance significantly with increasing training set size. ROC-AUC for SLA at 500 exams was comparable to PLA at 998 exams (P = 0.28). ROC-AUC was significantly different between SLA and PLA at same training set sizes, however the ROC-AUC difference decreased significantly from 200 to 998 training exams. Emulating PI-RADS ≥ 3 decisions, difference between PLA specificity of 0.12 [51/433] and SLA specificity of 0.13 [55/433] became undetectable (P = 1.0) at 998 exams. Emulating PI-RADS ≥ 4 decisions, at 998 exams, SLA specificity of 0.51 [221/433] remained higher than PLA specificity at 0.39 [170/433]. However, PLA specificity at 998 exams became comparable to SLA specificity of 0.37 [159/433] at 200 exams (P = 0.70). DATA CONCLUSION: Weakly supervised training of a classification CNN using patient-level-only annotation had lower performance compared to training with slice-wise annotations, but improved significantly faster with additional training data. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Weakly Supervised Depth Estimation for 3D Imaging with Single Camera Fringe Projection Profilometry.

Fringe projection profilometry (FPP) is widely used for high-accuracy 3D imaging. However, employing multiple sets of fringe patterns ensures 3D reconstruction accuracy while inevitably constraining the measurement speed. Conventional dual-frequency FPP reduces the number of fringe patterns for one reconstruction to six or fewer, but the highest period-number of fringe patterns generally is limited because of phase errors. Deep learning makes depth estimation from fringe images possible. Inspired by unsupervised monocular depth estimation, this paper proposes a novel, weakly supervised method of depth estimation for single-camera FPP. The trained network can estimate the depth from three frames of 64-period fringe images. The proposed method is more efficient in terms of fringe pattern efficiency by at least 50% compared to conventional FPP. The experimental results show that the method achieves competitive accuracy compared to the supervised method and is significantly superior to the conventional dual-frequency methods.

Weakly Supervised Pose Estimation of Surgical Instrument from a Single Endoscopic Image.

Instrument pose estimation is a key demand in computer-aided surgery, and its main challenges lie in two aspects: Firstly, the difficulty of obtaining stable corresponding image feature points due to the instruments' high refraction and complicated background, and secondly, the lack of labeled pose data. This study aims to tackle the pose estimation problem of surgical instruments in the current endoscope system using a single endoscopic image. More specifically, a weakly supervised method based on the instrument's image segmentation contour is proposed, with the effective assistance of synthesized endoscopic images. Our method consists of the following three modules: a segmentation module to automatically detect the instrument in the input image, followed by a point inference module to predict the image locations of the implicit feature points of the instrument, and a point back-propagatable Perspective-n-Point module to estimate the pose from the tentative 2D-3D corresponding points. To alleviate the over-reliance on point correspondence accuracy, the local errors of feature point matching and the global inconsistency of the corresponding contours are simultaneously minimized. Our proposed method is validated with both real and synthetic images in comparison with the current state-of-the-art methods.

A Semi-Automatic Magnetic Resonance Imaging Annotation Algorithm Based on Semi-Weakly Supervised Learning.

The annotation of magnetic resonance imaging (MRI) images plays an important role in deep learning-based MRI segmentation tasks. Semi-automatic annotation algorithms are helpful for improving the efficiency and reducing the difficulty of MRI image annotation. However, the existing semi-automatic annotation algorithms based on deep learning have poor pre-annotation performance in the case of insufficient segmentation labels. In this paper, we propose a semi-automatic MRI annotation algorithm based on semi-weakly supervised learning. In order to achieve a better pre-annotation performance in the case of insufficient segmentation labels, semi-supervised and weakly supervised learning were introduced, and a semi-weakly supervised learning segmentation algorithm based on sparse labels was proposed. In addition, in order to improve the contribution rate of a single segmentation label to the performance of the pre-annotation model, an iterative annotation strategy based on active learning was designed. The experimental results on public MRI datasets show that the proposed algorithm achieved an equivalent pre-annotation performance when the number of segmentation labels was much less than that of the fully supervised learning algorithm, which proves the effectiveness of the proposed algorithm.

CAC: Confidence-Aware Co-Training for Weakly Supervised Crack Segmentation.

Automatic crack segmentation plays an essential role in maintaining the structural health of buildings and infrastructure. Despite the success in fully supervised crack segmentation, the costly pixel-level annotation restricts its application, leading to increased exploration in weakly supervised crack segmentation (WSCS). However, WSCS methods inevitably bring in noisy pseudo-labels, which results in large fluctuations. To address this problem, we propose a novel confidence-aware co-training (CAC) framework for WSCS. This framework aims to iteratively refine pseudo-labels, facilitating the learning of a more robust segmentation model. Specifically, a co-training mechanism is designed and constructs two collaborative networks to learn uncertain crack pixels, from easy to hard. Moreover, the dynamic division strategy is designed to divide the pseudo-labels based on the crack confidence score. Among them, the high-confidence pseudo-labels are utilized to optimize the initialization parameters for the collaborative network, while low-confidence pseudo-labels enrich the diversity of crack samples. Extensive experiments conducted on the Crack500, DeepCrack, and CFD datasets demonstrate that the proposed CAC significantly outperforms other WSCS methods.

Diagnosis of Alzheimer Disease and Tauopathies on Whole-Slide Histopathology Images Using a Weakly Supervised Deep Learning Algorithm.

Neuropathologic assessment during autopsy is the gold standard for diagnosing neurodegenerative disorders. Neurodegenerative conditions, such as Alzheimer disease (AD) neuropathological change, are a continuous process from normal aging rather than categorical; therefore, diagnosing neurodegenerative disorders is a complicated task. We aimed to develop a pipeline for diagnosing AD and other tauopathies, including corticobasal degeneration (CBD), globular glial tauopathy, Pick disease, and progressive supranuclear palsy. We used a weakly supervised deep learning-based approach called clustering-constrained-attention multiple-instance learning (CLAM) on the whole-slide images (WSIs) of patients with AD (n = 30), CBD (n = 20), globular glial tauopathy (n = 10), Pick disease (n = 20), and progressive supranuclear palsy (n = 20), as well as nontauopathy controls (n = 21). Three sections (A: motor cortex; B: cingulate gyrus and superior frontal gyrus; and C: corpus striatum) that had been immunostained for phosphorylated tau were scanned and converted to WSIs. We evaluated 3 models (classic multiple-instance learning, single-attention-branch CLAM, and multiattention-branch CLAM) using 5-fold cross-validation. Attention-based interpretation analysis was performed to identify the morphologic features contributing to the classification. Within highly attended regions, we also augmented gradient-weighted class activation mapping to the model to visualize cellular-level evidence of the model's decisions. The multiattention-branch CLAM model using section B achieved the highest area under the curve (0.970 ± 0.037) and diagnostic accuracy (0.873 ± 0.087). A heatmap showed the highest attention in the gray matter of the superior frontal gyrus in patients with AD and the white matter of the cingulate gyrus in patients with CBD. Gradient-weighted class activation mapping showed the highest attention in characteristic tau lesions for each disease (eg, numerous tau-positive threads in the white matter inclusions for CBD). Our findings support the feasibility of deep learning-based approaches for the classification of neurodegenerative disorders on WSIs. Further investigation of this method, focusing on clinicopathologic correlations, is warranted.

Two-tiered deep-learning-based model for histologic diagnosis of Helicobacter gastritis.

AIMS: Helicobacter pylori (HP) infection is the most common cause of chronic gastritis worldwide. Due to the small size of HP and limited resolution, diagnosing HP infections is more difficult when using digital slides. METHODS AND RESULTS: We developed a two-tier deep-learning-based model for diagnosing HP gastritis. A whole-slide model was trained on 885 whole-slide images (WSIs) with only slide-level labels (positive or negative slides). An auxiliary model was trained on 824 areas with HP in nine positive WSIs and 446 negative WSIs for localizing HP. The whole-slide model performed well, with an area under the receiver operating characteristic curve (AUC) of 0.9739 (95% confidence interval [CI], 0.9545-0.9932). The calculated sensitivity and specificity were 93.3% and 90.1%, respectively, whereas those of pathologists were 93.3% and 84.2%, respectively. Using the auxiliary model, the highlighted areas of the localization maps had an average precision of 0.5796. CONCLUSIONS: HP gastritis can be diagnosed on haematoxylin-and-eosin-stained WSIs with human-level accuracy using a deep-learning-based model trained on slide-level labels and an auxiliary model for localizing HP and confirming the diagnosis. This two-tiered model can shorten the diagnostic process and reduce the need for special staining.

Inference of core needle biopsy whole slide images requiring definitive therapy for prostate cancer.

BACKGROUND: Prostate cancer is often a slowly progressive indolent disease. Unnecessary treatments from overdiagnosis are a significant concern, particularly low-grade disease. Active surveillance has being considered as a risk management strategy to avoid potential side effects by unnecessary radical treatment. In 2016, American Society of Clinical Oncology (ASCO) endorsed the Cancer Care Ontario (CCO) Clinical Practice Guideline on active surveillance for the management of localized prostate cancer. METHODS: Based on this guideline, we developed a deep learning model to classify prostate adenocarcinoma into indolent (applicable for active surveillance) and aggressive (necessary for definitive therapy) on core needle biopsy whole slide images (WSIs). In this study, we trained deep learning models using a combination of transfer, weakly supervised, and fully supervised learning approaches using a dataset of core needle biopsy WSIs (n=1300). In addition, we performed an inter-rater reliability evaluation on the WSI classification. RESULTS: We evaluated the models on a test set (n=645), achieving ROC-AUCs of 0.846 for indolent and 0.980 for aggressive. The inter-rater reliability evaluation showed s-scores in the range of 0.10 to 0.95, with the lowest being on the WSIs with both indolent and aggressive classification by the model, and the highest on benign WSIs. CONCLUSION: The results demonstrate the promising potential of deployment in a practical prostate adenocarcinoma histopathological diagnostic workflow system.

m6A-Maize: Weakly supervised prediction of m6A-carrying transcripts and m6A-affecting mutations in maize (Zea mays).

With the rapid development of high-throughput sequencing techniques nowadays, extensive attention has been paid to epitranscriptomics, which covers more than 150 distinct chemical modifications to date. Among that, N6-methyladenosine (m6A) modification has the most abundant existence, and it is also significantly related to varieties of biological processes. Meanwhile, maize is the most important food crop and cultivated throughout the world. Therefore, the study of m6A modification in maize has both economic and academic value. In this research, we proposed a weakly supervised learning model to predict the situation of m6A modification in maize. The proposed model learns from low-resolution epitranscriptome datasets (e.g., MeRIP-seq), which predicts the m6A methylation status of given fragments or regions. By taking advantage of our prediction model, we further identified traits-associated SNPs that may affect (add or remove) m6A modifications in maize, which may provide potential regulatory mechanisms at epitranscriptome layer. Additionally, a centralized online-platform was developed for m6A study in maize, which contains 58,838 experimentally validated maize m6A-containing regions including training and testing datasets, and a database for 2,578 predicted traits-associated m6A-affecting maize mutations. Furthermore, the online web server based on proposed weakly supervised model is available for predicting putative m6A sites from user-uploaded maize sequences, as well as accessing the epitranscriptome impact of user-interested maize SNPs on m6A modification. In all, our work provided a useful resource for the study of m6A RNA methylation in maize species. It is freely accessible at www.xjtlu.edu.cn/biologicalsciences/maize.

Objective assessment of stored blood quality by deep learning.

Stored red blood cells (RBCs) are needed for life-saving blood transfusions, but they undergo continuous degradation. RBC storage lesions are often assessed by microscopic examination or biochemical and biophysical assays, which are complex, time-consuming, and destructive to fragile cells. Here we demonstrate the use of label-free imaging flow cytometry and deep learning to characterize RBC lesions. Using brightfield images, a trained neural network achieved 76.7% agreement with experts in classifying seven clinically relevant RBC morphologies associated with storage lesions, comparable to 82.5% agreement between different experts. Given that human observation and classification may not optimally discern RBC quality, we went further and eliminated subjective human annotation in the training step by training a weakly supervised neural network using only storage duration times. The feature space extracted by this network revealed a chronological progression of morphological changes that better predicted blood quality, as measured by physiological hemolytic assay readouts, than the conventional expert-assessed morphology classification system. With further training and clinical testing across multiple sites, protocols, and instruments, deep learning and label-free imaging flow cytometry might be used to routinely and objectively assess RBC storage lesions. This would automate a complex protocol, minimize laboratory sample handling and preparation, and reduce the impact of procedural errors and discrepancies between facilities and blood donors. The chronology-based machine-learning approach may also improve upon humans' assessment of morphological changes in other biomedically important progressions, such as differentiation and metastasis.

Point Cloud Instance Segmentation with Inaccurate Bounding-Box Annotations.

Most existing point cloud instance segmentation methods require accurate and dense point-level annotations, which are extremely laborious to collect. While incomplete and inexact supervision has been exploited to reduce labeling efforts, inaccurate supervision remains under-explored. This kind of supervision is almost inevitable in practice, especially in complex 3D point clouds, and it severely degrades the generalization performance of deep networks. To this end, we propose the first weakly supervised point cloud instance segmentation framework with inaccurate box-level labels. A novel self-distillation architecture is presented to boost the generalization ability while leveraging the cheap but noisy bounding-box annotations. Specifically, we employ consistency regularization to distill self-knowledge from data perturbation and historical predictions, which prevents the deep network from overfitting the noisy labels. Moreover, we progressively select reliable samples and correct their labels based on the historical consistency. Extensive experiments on the ScanNet-v2 dataset were used to validate the effectiveness and robustness of our method in dealing with inexact and inaccurate annotations.

Weak Localization of Radiographic Manifestations in Pulmonary Tuberculosis from Chest X-ray: A Systematic Review.

Pulmonary tuberculosis (PTB) is a bacterial infection that affects the lung. PTB remains one of the infectious diseases with the highest global mortalities. Chest radiography is a technique that is often employed in the diagnosis of PTB. Radiologists identify the severity and stage of PTB by inspecting radiographic features in the patient's chest X-ray (CXR). The most common radiographic features seen on CXRs include cavitation, consolidation, masses, pleural effusion, calcification, and nodules. Identifying these CXR features will help physicians in diagnosing a patient. However, identifying these radiographic features for intricate disorders is challenging, and the accuracy depends on the radiologist's experience and level of expertise. So, researchers have proposed deep learning (DL) techniques to detect and mark areas of tuberculosis infection in CXRs. DL models have been proposed in the literature because of their inherent capacity to detect diseases and segment the manifestation regions from medical images. However, fully supervised semantic segmentation requires several pixel-by-pixel labeled images. The annotation of such a large amount of data by trained physicians has some challenges. First, the annotation requires a significant amount of time. Second, the cost of hiring trained physicians is expensive. In addition, the subjectivity of medical data poses a difficulty in having standardized annotation. As a result, there is increasing interest in weak localization techniques. Therefore, in this review, we identify methods employed in the weakly supervised segmentation and localization of radiographic manifestations of pulmonary tuberculosis from chest X-rays. First, we identify the most commonly used public chest X-ray datasets for tuberculosis identification. Following that, we discuss the approaches for weakly localizing tuberculosis radiographic manifestations in chest X-rays. The weakly supervised localization of PTB can highlight the region of the chest X-ray image that contributed the most to the DL model's classification output and help pinpoint the diseased area. Finally, we discuss the limitations and challenges of weakly supervised techniques in localizing TB manifestations regions in chest X-ray images.

Visibility Estimation Based on Weakly Supervised Learning under Discrete Label Distribution.

This paper proposes an end-to-end neural network model that fully utilizes the characteristic of uneven fog distribution to estimate visibility in fog images. Firstly, we transform the original single labels into discrete label distributions and introduce discrete label distribution learning on top of the existing classification networks to learn the difference in visibility information among different regions of an image. Then, we employ the bilinear attention pooling module to find the farthest visible region of fog in the image, which is incorporated into an attention-based branch. Finally, we conduct a cascaded fusion of the features extracted from the attention-based branch and the base branch. Extensive experimental results on a real highway dataset and a publicly available synthetic road dataset confirm the effectiveness of the proposed method, which has low annotation requirements, good robustness, and broad application space.

Cognitive Refined Augmentation for Video Anomaly Detection in Weak Supervision.

Weakly supervised video anomaly detection is a methodology that assesses anomaly levels in individual frames based on labeled video data. Anomaly scores are computed by evaluating the deviation of distances derived from frames in an unbiased state. Weakly supervised video anomaly detection encounters the formidable challenge of false alarms, stemming from various sources, with a major contributor being the inadequate reflection of frame labels during the learning process. Multiple instance learning has been a pivotal solution to this issue in previous studies, necessitating the identification of discernible features between abnormal and normal segments. Simultaneously, it is imperative to identify shared biases within the feature space and cultivate a representative model. In this study, we introduce a novel multiple instance learning framework anchored on a memory unit, which augments features based on memory and effectively bridges the gap between normal and abnormal instances. This augmentation is facilitated through the integration of an multi-head attention feature augmentation module and loss function with a KL divergence and a Gaussian distribution estimation-based approach. The method identifies distinguishable features and secures the inter-instance distance, thus fortifying the distance metrics between abnormal and normal instances approximated by distribution. The contribution of this research involves proposing a novel framework based on MIL for performing WSVAD and presenting an efficient integration strategy during the augmentation process. Extensive experiments were conducted on benchmark datasets XD-Violence and UCF-Crime to substantiate the effectiveness of the proposed model.

A Weakly Supervised Semantic Segmentation Model of Maize Seedlings and Weed Images Based on Scrawl Labels.

The task of semantic segmentation of maize and weed images using fully supervised deep learning models requires a large number of pixel-level mask labels, and the complex morphology of the maize and weeds themselves can further increase the cost of image annotation. To solve this problem, we proposed a Scrawl Label-based Weakly Supervised Semantic Segmentation Network (SL-Net). SL-Net consists of a pseudo label generation module, encoder, and decoder. The pseudo label generation module converts scrawl labels into pseudo labels that replace manual labels that are involved in network training, improving the backbone network for feature extraction based on the DeepLab-V3+ model and using a migration learning strategy to optimize the training process. The results show that the intersection over union of the pseudo labels that are generated by the pseudo label module with the ground truth is 83.32%, and the cosine similarity is 93.55%. In the semantic segmentation testing of SL-Net for image seedling of maize plants and weeds, the mean intersection over union and average precision reached 87.30% and 94.06%, which is higher than the semantic segmentation accuracy of DeepLab-V3+ and PSPNet under weakly and fully supervised learning conditions. We conduct experiments to demonstrate the effectiveness of the proposed method.

PosturePose: Optimized Posture Analysis for Semi-Supervised Monocular 3D Human Pose Estimation.

One motivation for studying semi-supervised techniques for human pose estimation is to compensate for the lack of variety in curated 3D human pose datasets by combining labeled 3D pose data with readily available unlabeled video data-effectively, leveraging the annotations of the former and the rich variety of the latter to train more robust pose estimators. In this paper, we propose a novel, fully differentiable posture consistency loss that is unaffected by camera orientation and improves monocular human pose estimators trained with limited labeled 3D pose data. Our semi-supervised monocular 3D pose framework combines biomechanical pose regularization with a multi-view posture (and pose) consistency objective function. We show that posture optimization was effective at decreasing pose estimation errors when applied to a 2D-3D lifting network (VPose3D) and two well-studied datasets (H36M and 3DHP). Specifically, the proposed semi-supervised framework with multi-view posture and pose loss lowered the mean per-joint position error (MPJPE) of leading semi-supervised methods by up to 15% (-7.6 mm) when camera parameters of unlabeled poses were provided. Without camera parameters, our semi-supervised framework with posture loss improved semi-supervised state-of-the-art methods by 17% (-15.6 mm decrease in MPJPE). Overall, our pose models compete favorably with other high-performing pose models trained under similar conditions with limited labeled data.

CNN-ViT Supported Weakly-Supervised Video Segment Level Anomaly Detection.

Video anomaly event detection (VAED) is one of the key technologies in computer vision for smart surveillance systems. With the advent of deep learning, contemporary advances in VAED have achieved substantial success. Recently, weakly supervised VAED (WVAED) has become a popular VAED technical route of research. WVAED methods do not depend on a supplementary self-supervised substitute task, yet they can assess anomaly scores straightway. However, the performance of WVAED methods depends on pretrained feature extractors. In this paper, we first address taking advantage of two pretrained feature extractors for CNN (e.g., C3D and I3D) and ViT (e.g., CLIP), for effectively extracting discerning representations. We then consider long-range and short-range temporal dependencies and put forward video snippets of interest by leveraging our proposed temporal self-attention network (TSAN). We design a multiple instance learning (MIL)-based generalized architecture named CNN-ViT-TSAN, by using CNN- and/or ViT-extracted features and TSAN to specify a series of models for the WVAED problem. Experimental results on publicly available popular crowd datasets demonstrated the effectiveness of our CNN-ViT-TSAN.

Weakly Supervised Breast Lesion Detection in Dynamic Contrast-Enhanced MRI.

Currently, obtaining accurate medical annotations requires high labor and time effort, which largely limits the development of supervised learning-based tumor detection tasks. In this work, we investigated a weakly supervised learning model for detecting breast lesions in dynamic contrast-enhanced MRI (DCE-MRI) with only image-level labels. Two hundred fifty-four normal and 398 abnormal cases with pathologically confirmed lesions were retrospectively enrolled into the breast dataset, which was divided into the training set (80%), validation set (10%), and testing set (10%) at the patient level. First, the second image series S2 after the injection of a contrast agent was acquired from the 3.0-T, T1-weighted dynamic enhanced MR imaging sequences. Second, a feature pyramid network (FPN) with convolutional block attention module (CBAM) was proposed to extract multi-scale feature maps of the modified classification network VGG16. Then, initial location information was obtained from the heatmaps generated using the layer class activation mapping algorithm (Layer-CAM). Finally, the detection results of breast lesion were refined by the conditional random field (CRF). Accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC) were utilized for evaluation of image-level classification. Average precision (AP) was estimated for breast lesion localization. Delong's test was used to compare the AUCs of different models for significance. The proposed model was effective with accuracy of 95.2%, sensitivity of 91.6%, specificity of 99.2%, and AUC of 0.986. The AP for breast lesion detection was 84.1% using weakly supervised learning. Weakly supervised learning based on FPN combined with Layer-CAM facilitated automatic detection of breast lesion.

A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations.

The automatic detection of cells in microscopy image sequences is a significant task in biomedical research. However, routine microscopy images with cells, which are taken during the process whereby constant division and differentiation occur, are notoriously difficult to detect due to changes in their appearance and number. Recently, convolutional neural network (CNN)-based methods have made significant progress in cell detection and tracking. However, these approaches require many manually annotated data for fully supervised training, which is time-consuming and often requires professional researchers. To alleviate such tiresome and labor-intensive costs, we propose a novel weakly supervised learning cell detection and tracking framework that trains the deep neural network using incomplete initial labels. Our approach uses incomplete cell markers obtained from fluorescent images for initial training on the Induced Pluripotent Stem (iPS) cell dataset, which is rarely studied for cell detection and tracking. During training, the incomplete initial labels were updated iteratively by combining detection and tracking results to obtain a model with better robustness. Our method was evaluated using two fields of the iPS cell dataset, along with the cell detection accuracy (DET) evaluation metric from the Cell Tracking Challenge (CTC) initiative, and it achieved 0.862 and 0.924 DET, respectively. The transferability of the developed model was tested using the public dataset FluoN2DH-GOWT1, which was taken from CTC; this contains two datasets with reference annotations. We randomly removed parts of the annotations in each labeled data to simulate the initial annotations on the public dataset. After training the model on the two datasets, with labels that comprise 10% cell markers, the DET improved from 0.130 to 0.903 and 0.116 to 0.877. When trained with labels that comprise 60% cell markers, the performance was better than the model trained using the supervised learning method. This outcome indicates that the model's performance improved as the quality of the labels used for training increased.