In digital pathology, tissue slides are scanned into Whole Slide Images (WSI) and pathologists first screen for diagnostically-relevant Regions of Interest (ROIs) before reviewing them. Screening for ...ROIs is a tedious and time-consuming visual recognition task which can be exhausting. The cognitive workload could be reduced by developing a visual aid to narrow down the visual search area by highlighting (or segmenting) regions of diagnostic relevance, enabling pathologists to spend more time diagnosing relevant ROIs. In this paper, we propose HistoSegNet, a method for semantic segmentation of histological tissue type (HTT). Using the HTT-annotated Atlas of Digital Pathology (ADP) database, we train a Convolutional Neural Network on the patch annotations, infer Gradient-Weighted Class Activation Maps, average overlapping predictions, and post-process the segmentation with a fully-connected Conditional Random Field. Our method out-performs more complicated weakly-supervised semantic segmentation methods and can generalize to other datasets without retraining.
One of the challenges facing the adoption of digital pathology workflows for clinical use is the need for automated quality control. As the scanners sometimes determine focus inaccurately, the ...resultant image blur deteriorates the scanned slide to the point of being unusable. Also, the scanned slide images tend to be extremely large when scanned at greater or equal 20X image resolution. Hence, for digital pathology to be clinically useful, it is necessary to use computational tools to quickly and accurately quantify the image focus quality and determine whether an image needs to be re-scanned. We propose a no-reference focus quality assessment metric specifically for digital pathology images that operate by using a sum of even-derivative filter bases to synthesize a human visual system-like kernel, which is modeled as the inverse of the lens' point spread function. This kernel is then applied to a digital pathology image to modify high-frequency image information deteriorated by the scanner's optics and quantify the focus quality at the patch level. We show in several experiments that our method correlates better with ground-truth z -level data than other methods, which is more computationally efficient. We also extend our method to generate a local slide-level focus quality heatmap, which can be used for automated slide quality control, and demonstrate the utility of our method for clinical scan quality control by comparison with subjective slide quality scores.
Effective mucus lavage and delivery of topical pharmaceuticals are central to successful management of chronic rhinosinusitis (CRS). The frontal sinus remains difficult to penetrate with topical ...therapies. This study evaluates the benefit of Draf III frontal dissection compared to traditional Draf IIa for distribution of topical therapies.
Fresh human cadaver heads were dissected sequentially with Draf IIa frontal sinusotomy and then Draf III procedures. Each cavity was irrigated with pediatric (120 mL) and adult (240 mL) irrigation bottles with 1/1000 10% fluorescein-labeled free water in 2 fixed positions (vertex and Frankfort horizontal). An endoscope at a fixed position within the frontal sinus recorded frontal sinus and frontal recess penetration. The images then underwent blinded evaluation of fluid distribution scored as 0 to 4 (nasal cavity only, frontal recess, medial one-half, lateral one-half, and lavage). Ordinal distribution score was analyzed with Kendall's tau-b.
Eight specimens (age 76 ± 11.2 years; 50% female) were assessed. Draf III was superior to Draf IIa in ability to achieve frontal sinus distribution of irrigation (90.6% vs 50.1%, p < 0.001). Vertex head position improved distribution (90.6% vs 50.1%, p < 0.001), was synergistic with Draf III (100% with 87.5% lavage, p < 0.001), but was unable to overcome Draf IIa (81.2% with 25% lavage, p < 0.001). Irrigation volume trended toward improved distribution with larger volume irrigations.
Successful treatment of sinonasal disease may require postoperative delivery of topical therapies. Draf III frontal sinusotomy achieves superior topical access, and access to the frontal sinus with Draf IIa appears limited, despite large volumes and positioning.
Computational Pathology (CPath) is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main objective for CPath ...is to develop infrastructure and workflows of digital diagnostics as an assistive CAD system for clinical pathology, facilitating transformational changes in the diagnosis and treatment of cancer that are mainly address by CPath tools. With evergrowing developments in deep learning and computer vision algorithms, and the ease of the data flow from digital pathology, currently CPath is witnessing a paradigm shift. Despite the sheer volume of engineering and scientific works being introduced for cancer image analysis, there is still a considerable gap of adopting and integrating these algorithms in clinical practice. This raises a significant question regarding the direction and trends that are undertaken in CPath. In this article we provide a comprehensive review of more than 800 papers to address the challenges faced in problem design all-the-way to the application and implementation viewpoints. We have catalogued each paper into a model-card by examining the key works and challenges faced to layout the current landscape in CPath. We hope this helps the community to locate relevant works and facilitate understanding of the field’s future directions. In a nutshell, we oversee the CPath developments in cycle of stages which are required to be cohesively linked together to address the challenges associated with such multidisciplinary science. We overview this cycle from different perspectives of data-centric, model-centric, and application-centric problems. We finally sketch remaining challenges and provide directions for future technical developments and clinical integration of CPath. For updated information on this survey review paper and accessing to the original model cards repository, please refer to GitHub. Updated version of this draft can also be found from arXiv.
Surgery in adult obstructive sleep apnea (OSA) has undergone significant advancement in recent years and continues to evolve. It is a modality of treatment used in the context of failed device use, ...specifically, failed continuous positive airway pressure or mandibular advancement splint. In this context, the role of surgery is either as salvage therapy or to facilitate better tolerance of device use. Other treatments such as weight loss, adjuvant nasal therapy (medical ± prephase nasal surgery) and positional devices may be combined with airway surgery. In general, patients with OSA are managed with in-hospital monitoring perioperatively.
Abstract Objectives To review the outcomes of endoscopic, open or a combination of both surgical modalities for laryngotracheal stenosis and establish which factors influence results. Methods Records ...of all children undergoing laryngotracheal procedures (excluding laryngomalacia and aspirated foreign bodies) by the Department of Otolaryngology at The Children's Hospital at Westmead between January 2003 and November 2011 were reviewed. Specific data on population, intervention, covariates and outcomes were recorded and analysed. Results A total of 104 patients undergoing 277 procedures were included. 211 (76%) of the procedures were endoscopic, remaining 66 (24%) open. Patients undergoing open surgery were more likely to have significant co-morbidity, prior intubation, require ICU admission or tracheostomy and have a longer hospital stay. 57 (54.8%) patients were successfully treated with a single procedure (48 endoscopic and 9 open). Of the endoscopic patients requiring further surgery, 16 were managed with multiple endoscopic procedures, whilst 12 underwent subsequent open procedures. Open surgery was performed on 66 patients, 63.6% (42/66) of all open procedures required further endoscopic intervention and 45.2% (19/42) of these avoided further open surgery. Conclusions Both open and endoscopic surgery have a role in laryngotracheal stenosis, and many patients benefit from a combination of both. Ultimately the decision depends on experience of the treating team, social considerations, and institutional capabilities. A multi-centre prospective data collection would be a useful tool to further investigate optimal management approach.
Recently proposed methods for weakly-supervised semantic segmentation have achieved impressive performance in predicting pixel classes despite being trained with only image labels which lack ...positional information. Because image annotations are cheaper and quicker to generate, weak supervision is more practical than full supervision for training segmentation algorithms. These methods have been predominantly developed to solve the background separation and partial segmentation problems presented by natural scene images and it is unclear whether they can be simply transferred to other domains with different characteristics, such as histopathology and satellite images, and still perform well. This paper evaluates state-of-the-art weakly-supervised semantic segmentation methods on natural scene, histopathology, and satellite image datasets and analyzes how to determine which method is most suitable for a given dataset. Our experiments indicate that histopathology and satellite images present a different set of problems for weakly-supervised semantic segmentation than natural scene images, such as ambiguous boundaries and class co-occurrence. Methods perform well for datasets they were developed on, but tend to perform poorly on other datasets. We present some practical techniques for these methods on unseen datasets and argue that more work is needed for a generalizable approach to weakly-supervised semantic segmentation. Our full code implementation is available on GitHub:
https://github.com/lyndonchan/wsss-analysis
.
To assess the validity of home sleep apnea test directed diagnosis and treatment of obstructive sleep apnea (OSA) in a real-life clinical setting and establish the extent to which clinical evaluation ...alters diagnosis and therapeutic intervention, in the context of the evolving realm of precision medicine.
Retrospective consecutive cohort study of 505 patients referred to a single center between 15th September 2015 to 14th September 2016, multidisciplinary specialist sleep clinic presenting with a home sleep apnea test prior to referral. We evaluated the effect of sleep medicine practitioner (SMP) and ear, nose, and throat surgeon (ENTS) review on patient diagnoses, disease severity, and management options in OSA.
Hundred and fifteen patients were included. Repeat evaluation with in-lab polysomnogram (PSG) was required in 46/115 (40.0%) of patients, of which 20/46 (43.5%) had OSA severity changed. Sleep medicine practitioner review decreased the need for repeat testing with formal in-lab PSG (
< 0.05) and increased patient acceptance of continuous positive airway pressure (CPAP) as a long-term management option for OSA. Sleep medicine practitioner/ENTS review resulted in discovery of a non-OSA related sleep disorder or change in OSA severity in 47.8% (55/115). Ear, nose, and throat surgeon review resulted in additional or changed diagnosis in 75.7% (87/115) of patients.
In the clinical assessment and diagnosis of OSA, patients should be reviewed by medical practitioners with an interest in sleep disorders to better navigate the complexities of assessment, as well as the identification of co-morbid conditions.
Introduction. Pharyngoesophageal diverticuli are a common cause of dysphagia; they are associated with various morbidities and a decreased quality of life. There are several different types of the ...diverticuli, and they are divided based on the anatomical location of origin relative to the cricopharyngeal muscle; these include Zenker’s, Killian-Jamieson’s, and Laimer’s diverticula. The authors present a unique case of pharyngoesophageal diverticulum that has not been previously described. Case Presentation. A 65-year-old male presented with a 12-month history of dysphagia and odynophagia for solids. Barium swallow revealed bilateral moderately sized diverticuli that altered in size during the different phases of swallow. CT scan of the neck with oral contrast further identified the anatomy of the diverticuli, arising between the hyoid bone and thyroid cartilage. Discussion. An external transcervical approach was utilised to successfully repair the diverticuli. Subsequent cricopharyngeal spasm was treated with botulinum toxin, and the patient recovered with no ongoing symptoms. The barium swallow study is a commonly utilised initial investigation as it is easy to perform and safe and has good diagnostic value. Definitive management usually involves either endoscopic or open surgery. This case depicts a unique case of a pharyngeal diverticulum arising between the hyoid bone and thyroid cartilage.
Objective
To assess olfactory outcomes as measured by an olfactory-specific quality of life (QOL) questionnaire in patients undergoing EESBS for sellar lesions.
Design
Retrospective case series.
...Setting
Tertiary academic medical center.
Participants
In total, 36 patients undergoing EESBS for lesions limited to the sella were evaluated.
Main Outcome Measures
The following were performed before and three months after surgery: 22-Item Sinonasal Outcomes Test (SNOT-22), University of Pennsylvania Smell Identification Test (UPSIT), and the Assessment of Self-reported Olfactory Functioning (ASOF), which has three domains: subjective olfactory capability scale (SOC), smell-related problems (SRP), and olfactory-related quality of life (ORQ).
Results
Median age at surgery was 52.5 years, with a median tumor size of 1.8 cm (range: 0.2 to 3.9 cm). Pre- and postoperative median scores were 35 34, 36.2 and 34.5 32, 36 for UPSIT, 21 7.5, 33.5 and 21.5 6.8, 35.7 for SNOT-22, 10 9, 10 and 9 8, 10 for ASOF-SOC, 5 4.8, 5 and 4.5 4, 5 for ASOF-SRP, and 5 5, 5 and 5 4.5, 5 for ASOF-ORQ. There was no significant change in the two of the three domains of the ASOF. Correlation between ASOF and UPSIT scores were weak. Older age and larger tumor size were associated with worsened olfaction after surgery.
Conclusions
Patients did not experience significant changes in olfactory-specific QOL three months after EESBS, as measured by two domains of the ASOF. The ASOF may serve as a useful adjunctive tool for assessing olfaction after surgery. The lack of correlation between UPSIT and ASOF suggests the need for more research in subjective olfactory-related quality of life after surgery.