Evaluation of free DIEP flap complications in the setting of previous gynecological operations.

BACKGROUND: Autologous tissue breast reconstruction with free deep inferior epigastric perforator (DIEP) flaps is reliable with reproducible results and very few contraindications. However, previous surgery may compromise the abdominal donor site due to injury to the vascular pedicle. The purpose of the current study is to evaluate the effects of prior abdominal surgery on need for changes to the operative plan, intraoperative complications, and postoperative flap compromise. PATIENTS AND METHODS: A retrospective review of all patients undergoing breast reconstruction with free tissue transfer from the abdomen was performed. RESULTS: A total of 733 free abdominal flaps were performed in 478 patients during the study period. Two hundred sixty-two (54.8%) patients had prior abdominal surgery with 24.8% laparoscopic/robotic versus 56.9% open versus 18.3% both, 21.4% general surgery versus 60.7% gynecological versus 17.9% both, and 97.7% elective versus 1.1% emergent versus 1.1% both. There were 15 total flap losses (2.0%) and 2 partial flap losses (0.3%). Intraoperative complications and changes in the operative plan occurred in 13 flaps (1.8%) with 84.6% having prior gynecological surgery (p = .0001). CONCLUSIONS: Free DIEP flap breast reconstruction is becoming more commonplace with a low risk of complications. Although DIEP flaps are still possible in the setting of prior abdominal surgery, there is a higher risk of damage to the deep inferior epigastric pedicle in patients who have had emergency Cesarean sections or hysterectomy. Conducting a focused history may prepare the reconstructive microsurgeon to address and to avoid potential intraoperative complications.

Phrenic Nerve Reconstruction for Effective Surgical Treatment of Diaphragmatic Paralysis.

ABSTRACT: Diaphragmatic paralysis due to phrenic nerve injury may cause orthopnea, exertional dyspnea, and sleep-disordered breathing. Phrenic nerve reconstruction may relieve symptoms and improve respiratory function. A retrospective review of 400 consecutive patients undergoing phrenic nerve reconstruction for diaphragmatic paralysis at 2 tertiary treatment centers was performed between 2007 and 2019. Symptomatic patients were identified, and the diagnosis was confirmed on radiographic evaluations. Assessment parameters included pulmonary spirometry (forced expiratory volume in 1 second and FVC), maximal inspiratory pressure, compound muscle action potentials, diaphragm thickness, chest fluoroscopy, and Short Form 36 Health Survey Questionnaire (SF-36) survey. There were 81 females and 319 males with an average age of 54 years (range, 19-79 years). The mean duration from diagnosis to surgery was 29 months (range, 1-320 months). The most common etiologies were acute or chronic injury (29%), interscalene nerve block (17%), and cardiothoracic surgery (15%). The mean improvements in forced expiratory volume in 1 second and FVC at 1 year were 10% (P < 0.01) and 8% (P < 0.05), respectively. At 2-year follow-up, the corresponding values were 22% (P < 0.05) and 18% (P < 0.05), respectively. Improvement on chest fluoroscopy was demonstrated in 63% and 71% of patients at 1 and 2-year follow-up, respectively. There was a 20% (P < 0.01) improvement in maximal inspiratory pressure, and compound muscle action potentials increased by 82% (P < 0.001). Diaphragm thickness demonstrated a 27% (P < 0.01) increase, and SF-36 revealed a 59% (P < 0.001) improvement in physical functioning. Symptomatic diaphragmatic paralysis should be considered for surgical treatment. Phrenic nerve reconstruction can achieve symptomatic relief and improve respiratory function. Increasing spirometry and improvements on Sniff from 1 to 2 years support incremental recovery with longer follow-up.

Comparison of Phasix, polypropylene, and primary closure of the abdominal donor site after bilateral free flap breast reconstruction: Long-term evaluation of abdominal hernia and bulge formation.

BACKGROUND: Abdominal free flap harvest for breast reconstruction may result in significant morbidity in terms of hernias and bulges. Reinforcement of the donor site with mesh has been recommended to minimize the risk of hernias and bulges, but no studies exist evaluating the optimal type of mesh. Polypropylene has traditionally been used but the development of Phasix restorable mesh may be a reasonable alternative. Here, we compared the use of Phasix to polypropylene and primary closure and hypothesize that the former has lower rates of abdominal morbidity in the long term. PATIENTS AND METHODS: A retrospective review of all patients undergoing bilateral free flap breast reconstruction from the abdomen was performed while patients with pedicle flaps or alternative donor sites were excluded. Patient demographics, medical/surgical history, cancer treatments, and flap type were analyzed. All patients were monitored for a minimum of 2 years for early donor site complications as well as hernia/bulges. RESULTS: Sixty-six consecutive patients were included (40 patients with Phasix, 20 patients with polypropylene, and 6 patients with primary closure). Use of Phasix mesh resulted in higher initial operative costs ($2,750 vs. $72 vs. $0). Two patients with polypropylene mesh and one patient undergoing primary closure developed an abdominal bulge in an average follow-up of 25.2 months (11.5% vs. 0%, p = .04). CONCLUSIONS: Mesh placement for abdominal wall reinforcement after bilateral free flap breast reconstruction minimizes the risk of hernias and bulges. Although Phasix results in increased initial costs, abdominal morbidity is significantly decreased after follow-up beyond 2 years.

Wound area measurement with 3D transformation and smartphone images.

BACKGROUND: Quantitative areas is of great measurement of wound significance in clinical trials, wound pathological analysis, and daily patient care. 2D methods cannot solve the problems caused by human body curvatures and different camera shooting angles. Our objective is to simply collect wound areas, accurately measure wound areas and overcome the shortcomings of 2D methods. RESULTS: We propose a method with 3D transformation to measure wound area on a human body surface, which combines structure from motion (SFM), least squares conformal mapping (LSCM), and image segmentation. The method captures 2D images of wound, which is surrounded by adhesive tape scale next to it, by smartphone and implements 3D reconstruction from the images based on SFM. Then it uses LSCM to unwrap the UV map of the 3D model. In the end, it utilizes image segmentation by interactive method for wound extraction and measurement. Our system yields state-of-the-art results on a dataset of 118 wounds on 54 patients, and performs with an accuracy of 0.97. The Pearson correlation, standardized regression coefficient and adjusted R square of our method are 0.999, 0.895 and 0.998 respectively. CONCLUSIONS: A smartphone is used to capture wound images, which lowers costs, lessens dependence on hardware, and avoids the risk of infection. The quantitative calculation of the 3D wound area is realized, solving the challenges that 2D methods cannot and achieving a good accuracy.

Mapping anatomical related entities to human body parts based on wikipedia in discharge summaries.

*: Background Consisting of dictated free-text documents such as discharge summaries, medical narratives are widely used in medical natural language processing. Relationships between anatomical entities and human body parts are crucial for building medical text mining applications. To achieve this, we establish a mapping system consisting of a Wikipedia-based scoring algorithm and a named entity normalization method (NEN). The mapping system makes full use of information available on Wikipedia, which is a comprehensive Internet medical knowledge base. We also built a new ontology, Tree of Human Body Parts (THBP), from core anatomical parts by referring to anatomical experts and Unified Medical Language Systems (UMLS) to make the mapping system efficacious for clinical treatments. *: Result The gold standard is derived from 50 discharge summaries from our previous work, in which 2,224 anatomical entities are included. The F1-measure of the baseline system is 70.20%, while our algorithm based on Wikipedia achieves 86.67% with the assistance of NEN. *: Conclusions We construct a framework to map anatomical entities to THBP ontology using normalization and a scoring algorithm based on Wikipedia. The proposed framework is proven to be much more effective and efficient than the main baseline system.

Interrater agreement between American and Chinese sleep centers according to the 2014 AASM standard.

OBJECTIVES: To determine inter-lab reliability in sleep stage scoring using the 2014 American Academy of Sleep Medicine (AASM) manual. To understand in-depth reasons for disagreement and provide suggestions for improvement. METHODS: This study consisted of 40 all-night polysomnographys (PSGs) from different samples. PSGs were segmented into 37,642 30-s epochs. Five doctors from China and two doctors from America scored the epochs following the 2014 AASM standard. Scoring disagreement between two centers was evaluated using Cohen's kappa (κ). After visual inspection of PSGs of deviating scorings, potential disagreement reasons were analyzed. RESULTS: Inter-lab reliability yielded a substantial degree (κ = 0.75 ± 0.01). Scoring for stage W (κ = 0.89) and R (κ = 0.87) achieved the highest agreement, while stage N1 (κ = 0.45) reflected the lowest. Considering the relative disagreement ratio, N2-N3 (22.09%), W-N1 (19.68%), and N1-N2 (18.75%) were the most frequent combinations of discrepancy. American and Chinese doctors showed certain characteristics in the scoring of discrepancy combination W-N1, N1-N2, and N2-N3. There are seven reasons for disagreement, namely "on-threshold characteristic" (29.21%), "context influence" (18.06%), "characteristic identification difficulty" (8.81%), "arousal-wake confusion" (7.57%), "derivation inconsistence" (2.15%), "on-borderline characteristic" (0.92%), and "misrecognition" (33.27%). CONCLUSIONS: This study demonstrated the sleep stage scoring agreement of the 2014 AASM manual and explored potential sources of labeling ambiguity. Improvement measures were suggested accordingly to help remove ambiguity for scorers and improve scoring reliability at the international level.

Advancements in imaging technology for microvascular free tissue transfer.

The use of preoperative imaging has become routine for many reconstructive microsurgeons to help localize perforators for planning of microvascular free flaps. However, with advancements in imaging technology, perforator mapping represents only one potential benefit as virtual planning and medical modeling, and flap tissue perfusion are also rapidly becoming commonplace and the standard of care for many surgeons who perform high-volume free flap reconstruction for the breast, head and neck, torso, and the extremities.

Microneurosurgical treatment options in peripheral nerve compression syndromes after chemotherapy and radiation treatment.

Chemotherapy-induced peripheral neuropathy and radiation-induced brachial plexopathy are extremely debilitating conditions which can occur after treatment of malignancy. Unfortunately, the diagnosis can be elusive, and this dilemma is further compounded by the lack of efficacious therapeutics to prevent the onset of neurotoxicity before initiating chemotherapy or radiation or to treat these sequelae after treatment. However, microsurgical nerve decompression can provide these patients with a viable option to treat this complication.

Parallel multiple instance learning for extremely large histopathology image analysis.

BACKGROUND: Histopathology images are critical for medical diagnosis, e.g., cancer and its treatment. A standard histopathology slice can be easily scanned at a high resolution of, say, 200,000×200,000 pixels. These high resolution images can make most existing imaging processing tools infeasible or less effective when operated on a single machine with limited memory, disk space and computing power. RESULTS: In this paper, we propose an algorithm tackling this new emerging "big data" problem utilizing parallel computing on High-Performance-Computing (HPC) clusters. Experimental results on a large-scale data set (1318 images at a scale of 10 billion pixels each) demonstrate the efficiency and effectiveness of the proposed algorithm for low-latency real-time applications. CONCLUSIONS: The framework proposed an effective and efficient system for extremely large histopathology image analysis. It is based on the multiple instance learning formulation for weakly-supervised learning for image classification, segmentation and clustering. When a max-margin concept is adopted for different clusters, we obtain further improvement in clustering performance.

Large scale tissue histopathology image classification, segmentation, and visualization via deep convolutional activation features.

BACKGROUND: Histopathology image analysis is a gold standard for cancer recognition and diagnosis. Automatic analysis of histopathology images can help pathologists diagnose tumor and cancer subtypes, alleviating the workload of pathologists. There are two basic types of tasks in digital histopathology image analysis: image classification and image segmentation. Typical problems with histopathology images that hamper automatic analysis include complex clinical representations, limited quantities of training images in a dataset, and the extremely large size of singular images (usually up to gigapixels). The property of extremely large size for a single image also makes a histopathology image dataset be considered large-scale, even if the number of images in the dataset is limited. RESULTS: In this paper, we propose leveraging deep convolutional neural network (CNN) activation features to perform classification, segmentation and visualization in large-scale tissue histopathology images. Our framework transfers features extracted from CNNs trained by a large natural image database, ImageNet, to histopathology images. We also explore the characteristics of CNN features by visualizing the response of individual neuron components in the last hidden layer. Some of these characteristics reveal biological insights that have been verified by pathologists. According to our experiments, the framework proposed has shown state-of-the-art performance on a brain tumor dataset from the MICCAI 2014 Brain Tumor Digital Pathology Challenge and a colon cancer histopathology image dataset. CONCLUSIONS: The framework proposed is a simple, efficient and effective system for histopathology image automatic analysis. We successfully transfer ImageNet knowledge as deep convolutional activation features to the classification and segmentation of histopathology images with little training data. CNN features are significantly more powerful than expert-designed features.

Asymptomatic Deep Peroneal Vein Thrombosis During Free Fibula Flap Harvest: A Review of the Literature, Strategies for Preoperative Assessment, and an Algorithm for Reconstruction.

The free fibula flap is the preferred reconstructive method for oncologic defects of the mandible. Arterial inflow of the extremity is routinely evaluated with several modalities; however, venous screening is rarely performed. Patients with cancer are at elevated risk of occult deep venous thrombosis (DVT). An asymptomatic thrombus encountered during free fibula reconstruction is a serious concern. Although such cases have been reported, we suspect the incidence of DVT during fibula free flap harvest is underappreciated. This monograph uses a case example to review risk factors for occult DVT, present a strategy for preoperative assessment, and provide a reconstructive algorithm to for mandibular reconstruction in such instances.

Comprehensive Evaluation of Risk Factors and Management of Impending Flap Loss in 2138 Breast Free Flaps.

Loss of a breast free flap is a relatively rare but catastrophic occurrence. Our study aims to identify risk factors for flap loss and to assess whether different salvage techniques affect flap salvage. We performed a retrospective review of all breast free flaps performed at a single institution from 2000 to 2010. Overall, 2138 flaps were performed in 1608 patients (unilateral, 1120 and bilateral, 488) with 44 flap losses (2.1%). Age, body mass index, smoking, radiation, chemotherapy, and surgeon experience did not affect flap loss. Abdominal flaps based on a single perforator were at significantly higher risk for flap loss compared with flaps based on multiple perforators (P = 0.0007). Subgroup analysis of the subset of 166 compromised free flaps (flaps requiring a return to the operating room, an intraoperative anastomotic revision, or loss/partial loss of a free flap) demonstrated deep inferior epigastric perforator, and other flaps (superficial inferior epigastric artery and superior gluteal artery perforator) were significantly associated with flap loss [odds ratio (OR) 5.20; P = 0.03 and OR 6.91; P = 0.0004, respectively] compared with transverse rectus abdominis myocutaneous and muscle-sparing transverse rectus abdominis myocutaneous flaps. Although an intraoperative complication was not associated with a flap loss, the need for a reoperation was strongly predictive (P < 0.0001). Flap salvage was the highest within the first 24 hours (83.7%) and significantly less between days 1 and 3 (38.6%; P < 0.0001) and beyond 4 days (29.4%; P < 0.0001). Longer ischemia time was significantly associated with flap loss (P = 0.04). Salvage techniques (aspirin, heparinzation, thrombectomy, and thrombolytic) had no impact on flap salvage rates. Heparinization and thrombolytics were associated with higher loss rates (OR 3.40; P = 0.003 and OR 10.36; P < 0.0001, respectively). Free flap loss following breast reconstruction is multifactorial with higher losses in superficial inferior epigastric artery and gluteal flaps, single-perforator abdominal flaps, and longer ischemia times. Salvage rates are most successful within the first 24 hours, and the use of heparinization, aspirin, and thrombolytics does not improve salvage rates.

Bilingual term alignment from comparable corpora in English discharge summary and Chinese discharge summary.

BACKGROUND: Electronic medical record (EMR) systems have become widely used throughout the world to improve the quality of healthcare and the efficiency of hospital services. A bilingual medical lexicon of Chinese and English is needed to meet the demand for the multi-lingual and multi-national treatment. We make efforts to extract a bilingual lexicon from English and Chinese discharge summaries with a small seed lexicon. The lexical terms can be classified into two categories: single-word terms (SWTs) and multi-word terms (MWTs). For SWTs, we use a label propagation (LP; context-based) method to extract candidates of translation pairs. For MWTs, which are pervasive in the medical domain, we propose a term alignment method, which firstly obtains translation candidates for each component word of a Chinese MWT, and then generates their combinations, from which the system selects a set of plausible translation candidates. RESULTS: We compare our LP method with a baseline method based on simple context-similarity. The LP based method outperforms the baseline with the accuracies: 4.44% Acc1, 24.44% Acc10, and 62.22% Acc100, where AccN means the top N accuracy. The accuracy of the LP method drops to 5.41% Acc10 and 8.11% Acc20 for MWTs. Our experiments show that the method based on term alignment improves the performance for MWTs to 16.22% Acc10 and 27.03% Acc20. CONCLUSIONS: We constructed a framework for building an English-Chinese term dictionary from discharge summaries in the two languages. Our experiments have shown that the LP-based method augmented with the term alignment method will contribute to reduction of manual work required to compile a bilingual sydictionary of clinical terms.

Choosing the optimal timing for contralateral symmetry procedures after unilateral free flap breast reconstruction.

Achieving symmetry in unilateral free flap breast reconstruction often requires a contralateral procedure; however, no large studies exist that examine the factors related to revisions performed on the contralateral breast. The present study examines the relationship between revision and complication rate, and the type and timing of the contralateral procedure. Retrospective analysis was performed of all unilateral free flap breast reconstructions from January 2000 to December 2010 at a single academic institution. Overall, 1120 patients underwent unilateral free flap breast reconstruction with 558 (49.8%) patients undergoing a contralateral procedure, 154 (27.6%) immediate and 404 (72.4%) delayed. Contralateral procedures included 106 augmentations, 168 reductions, 240 mastopexies, and 37 augmentation-mastopexies. Revision of the symmetry procedure was performed in 114 (20.8%) patients. Augmentation and mastopexy were associated with significantly higher revision rates when performed immediately. The complication rate was higher in immediate contralateral procedures than delayed [15 (9.7%) vs 16 (4.0%), P = 0.01]. The average number of procedures per patient was significantly higher in delayed contralateral procedures than immediate (2.45 vs 1.84, P < 0.0005). In summary, approximately half of patients undergoing a unilateral free flap for breast reconstruction will also undergo a contralateral balancing procedure. Immediate contralateral augmentation and mastopexy carry a higher revision rate and consideration should be given to performing them in a staged fashion. There were no differences in the rate of revisions for breast reductions, and therefore, performance of simultaneous contralateral reduction is a reasonable option. Although complication rates were higher in the immediate cohort, overall "symmetry" was achieved in significantly fewer operations.

Recent trends in resident career choices after plastic surgery training.

The purpose of this study is to determine the initial career choice of plastic surgery residents after completion of training during the last five years and to identify any factors that may influence choice of career path. Demographic data were obtained from graduates of Accreditation Council for Graduate Medical Education (ACGME)-accredited US plastic surgery residency programs between the years of 2005 and 2010. The type of practice and pursuit of fellowship were recorded for each graduate. Sex, age at graduation, marital status, dependents, advanced degrees, previous research, type of training program, primary residency, and length of plastic surgery training were also documented. Comparison of outcomes between the two plastic surgery training pathways (integrated vs independent) was analyzed. Data were collected for 424 graduates from 37 different training programs. Of these programs, 11% were from the West coast, 32% from Midwest, 33% from East coast, and 24% from the South. Seventy-nine percent of residents were male, mean age at graduation was 35 (2.89) years. Forty-nine percent of residents were married, 30% had one or more dependents, 6% had advanced degrees, and 18% had previous research experience. Fifty-eight percent of graduates were from independent programs. Forty-eight percent of residents pursued private practice immediately after graduation, 8% pursued academic practice, 41% pursued specialty fellowships, and 3% had military commitments. Most of the residents chose to pursue private practice on completion of residency. Independent residents were significantly more likely to pursue private practice immediately compared to integrated/combined residents. No other factors were significant for practice choice.

Salvage rates of compromised free flap breast reconstruction after recurrent thrombosis.

BACKGROUND: Microvascular complications after free flap breast reconstruction are devastating problems that increase patient morbidity and potentially lead to flap loss. Yet, there is a dearth of literature about rates of free flap salvage after recurrent vascular thromboses. METHODS: A retrospective review of all patients undergoing microvascular breast reconstruction at UCLA Medical Center from January 1991 to June 2010 was conducted. The incidence of microvascular thrombosis was evaluated and rates of flap salvage and complications were specifically analyzed after a single microvascular revision (Single Event), 2 or more revisions (Multiple Event), and delayed presentation (>2 days) with attempted salvage (Delayed Event). RESULTS: During the study period, 2094 free flap breast reconstructions were evaluated. Of these, 75 (3.6%) flaps suffered a microvascular complication and 16 (0.76%) flaps were lost. The overall salvage rate was 78.7% (59/75) with the highest salvage rate of 95.9% (47/49) for Single Events. Multiple Events had a salvage rate of 53.3% (8/15), whereas Delayed Events had a salvage rate of 27.3% (3/11). The salvage rate decreased with repeated microvascular events (P < 0.01). In the Multiple Event group, vascular conversion (alternate recipient vessel) correlated with improved flap salvage (87.5%), whereas the lack thereof was associated with flap loss (P < 0.001). CONCLUSIONS: The salvage rate of free flap breast reconstruction diminishes dramatically with recurrent microvascular complications, but can be improved with vascular conversion. The salvage rate in cases of delayed presentation is even worse confirming the need for vigilant postoperative monitoring and aggressive intervention in the setting of flap compromise.

Chest wall reconstruction for sternal dehiscence after open heart surgery.

BACKGROUND: Sternal dehiscence is a grave complication after open heart surgery. Sternal debridement and flap coverage are the mainstays of therapy, but no consensus exists regarding the appropriate level of debridement. More recently, the use of vacuum-assisted closure devices has been advocated as a bridge to definitive closure, but indications for use remain incompletely defined. MATERIALS AND METHODS: A retrospective review of all chest wall reconstructions performed from January 2000 to December 2010 was conducted. The type of operative management was evaluated to assess morbidity, mortality, and length of hospital stay. RESULTS: Fifty-four patients underwent chest wall reconstruction for poststernotomy mediastinitis. Of these patients, 24 underwent conservative sternal debridement with flap closure, 24 underwent radical sternectomy including resection of the costal cartilages followed by flap closure, and 6 underwent radical sternectomy with vacuum-assisted closure therapy followed by flap closure in a delayed fashion. There were 15 patients in the conservative group and 8 patients in the radical sternectomy group who developed postoperative complications (62.5% vs 33.3%, P < 0.05). The conservative sternectomy group had more serious complications requiring reoperation compared to the radical sternectomy group (86.7% vs 25.0%, P < 0.05). The most common complication in the former group was flap dehiscence (8/15, 53.3%), whereas that in the latter group was a superficial wound infection (6/8, 75.0%). There was no significant difference in mortality (25.0% vs 25.0%, P > 0.05%) or length of hospital stay. CONCLUSIONS: Radical sternectomy including the costal cartilages is associated with lower rates of surgical morbidity and reoperation, but not mortality.

Narrative review of patient-reported outcomes of breast reconstruction.

Background and Objective: The treatment of breast cancer encompasses both the elimination of malignancy as well as reconstruction after tumor extirpation. Although the patient may have had successful treatment of her breast cancer, the resulting disfigurement and deformity can have a substantial impact on her physical and mental well-being. Breast reconstruction affords these patients the opportunity to correct these deformities and potentially to improve their quality of life. The current literature review evaluates patient-reported outcomes for the various options of breast reconstruction that are most commonly performed. Methods: A literature review on PubMed with the key words "patient-reported outcomes", "breast reconstruction", and "breast cancer" yielded 738 results, which were screened. Articles that specifically focused on patient-reported outcomes after various types of breast reconstruction were evaluated and included in this literature review. Key Content and Findings: The main options of alloplastic reconstruction, autologous tissue reconstruction, and oncoplastic reconstruction were reviewed and found to demonstrate high levels of patient satisfaction. Although there is no clear superior option, patient-reported outcomes demonstrate improved well-being compared to no reconstruction. Conclusions: Breast reconstruction provides the opportunity to correct the deformities after breast cancer treatment making it a crucial component of comprehensive cancer care. A variety of reconstructive options are available which can be tailored to each individual patient to achieve the optimal results for that particular patient. Therefore patient-reported outcomes are paramount to gauge the true success of not only breast cancer treatment but also reconstructive aspects after treatment.

Weakly supervised histopathology image segmentation with self-attention.

Accurate segmentation in histopathology images at pixel-level plays a critical role in the digital pathology workflow. The development of weakly supervised methods for histopathology image segmentation liberates pathologists from time-consuming and labor-intensive works, opening up possibilities of further automated quantitative analysis of whole-slide histopathology images. As an effective subgroup of weakly supervised methods, multiple instance learning (MIL) has achieved great success in histopathology images. In this paper, we specially treat pixels as instances so that the histopathology image segmentation task is transformed into an instance prediction task in MIL. However, the lack of relations between instances in MIL limits the further improvement of segmentation performance. Therefore, we propose a novel weakly supervised method called SA-MIL for pixel-level segmentation in histopathology images. SA-MIL introduces a self-attention mechanism into the MIL framework, which captures global correlation among all instances. In addition, we use deep supervision to make the best use of information from limited annotations in the weakly supervised method. Our approach makes up for the shortcoming that instances are independent of each other in MIL by aggregating global contextual information. We demonstrate state-of-the-art results compared to other weakly supervised methods on two histopathology image datasets. It is evident that our approach has generalization ability for the high performance on both tissue and cell histopathology datasets. There is potential in our approach for various applications in medical images.

3D Segmentation Guided Style-Based Generative Adversarial Networks for PET Synthesis.

Potential radioactive hazards in full-dose positron emission tomography (PET) imaging remain a concern, whereas the quality of low-dose images is never desirable for clinical use. So it is of great interest to translate low-dose PET images into full-dose. Previous studies based on deep learning methods usually directly extract hierarchical features for reconstruction. We notice that the importance of each feature is different and they should be weighted dissimilarly so that tiny information can be captured by the neural network. Furthermore, the synthesis on some regions of interest is important in some applications. Here we propose a novel segmentation guided style-based generative adversarial network (SGSGAN) for PET synthesis. (1) We put forward a style-based generator employing style modulation, which specifically controls the hierarchical features in the translation process, to generate images with more realistic textures. (2) We adopt a task-driven strategy that couples a segmentation task with a generative adversarial network (GAN) framework to improve the translation performance. Extensive experiments show the superiority of our overall framework in PET synthesis, especially on those regions of interest.