AlterNet-K: a small and compact model for the detection of glaucoma.

Glaucoma is one of the leading causes of permanent blindness in the world. It is caused due to an increase in the intraocular pressure within the eye that harms the optic nerve. People suffering from Glaucoma often do not notice any changes in their vision in the early stages. However, as it progresses, Glaucoma usually leads to vision loss that is irreversible in many cases. Thus, early diagnosis of this eye disease is of critical importance. The fundus image is one of the most used diagnostic tools for glaucoma detection. However, drawing accurate insights from these images requires them to be manually analyzed by medical experts, which is a time-consuming process. In this work, we propose a parameter-efficient AlterNet-K model based on an alternating design pattern, which combines ResNets and multi-head self-attention (MSA) to leverage their complementary properties to improve the generalizability of the overall model. The model was trained on the Rotterdam EyePACS AIROGS dataset, comprising 113,893 colour fundus images from 60,357 subjects. The AlterNet-K model outperformed transformer models such as ViT, DeiT-S, and Swin transformer, standard DCNN models including ResNet, EfficientNet, MobileNet and VGG with an accuracy of 0.916, AUROC of 0.968 and F1 score of 0.915. The results indicate that smaller CNN models combined with self-attention mechanisms can achieve high classification accuracies. Small and compact Resnet models combined with MSA outperform their larger counterparts. The models in this work can be extended to handle classification tasks in other medical imaging domains.

Customized Deep Learning Classifier for Detection of Acute Lymphoblastic Leukemia Using Blood Smear Images.

Acute lymphoblastic leukemia (ALL) is a rare type of blood cancer caused due to the overproduction of lymphocytes by the bone marrow in the human body. It is one of the common types of cancer in children, which has a fair chance of being cured. However, this may even occur in adults, and the chances of a cure are slim if diagnosed at a later stage. To aid in the early detection of this deadly disease, an intelligent method to screen the white blood cells is proposed in this study. The proposed intelligent deep learning algorithm uses the microscopic images of blood smears as the input data. This algorithm is implemented with a convolutional neural network (CNN) to predict the leukemic cells from the healthy blood cells. The custom ALLNET model was trained and tested using the microscopic images available as open-source data. The model training was carried out on Google Collaboratory using the Nvidia Tesla P-100 GPU method. Maximum accuracy of 95.54%, specificity of 95.81%, sensitivity of 95.91%, F1-score of 95.43%, and precision of 96% were obtained by this accurate classifier. The proposed technique may be used during the pre-screening to detect the leukemia cells during complete blood count (CBC) and peripheral blood tests.

Randomized clinical trial of deep brain stimulation for poststroke pain.

OBJECTIVE: The experience with deep brain stimulation (DBS) for pain is largely based on uncontrolled studies targeting the somatosensory pathways, with mixed results. We hypothesized that targeting limbic neural pathways would modulate the affective sphere of pain and alleviate suffering. METHODS: We conducted a prospective, double-blinded, randomized, placebo-controlled, crossover study of DBS targeting the ventral striatum/anterior limb of the internal capsule (VS/ALIC) in 10 patients with poststroke pain syndrome. One month after bilateral DBS, patients were randomized to active DBS or sham for 3 months, followed by crossover for another 3-month period. The primary endpoint was a ≥50% improvement on the Pain Disability Index in 50% of patients with active DBS compared to sham. This 6-month blinded phase was followed by an 18-month open stimulation phase. RESULTS: Nine participants completed randomization. Although this trial was negative for its primary and secondary endpoints, we did observe significant differences in multiple outcome measures related to the affective sphere of pain (eg, Montgomery-Åsberg Depression Rating Scale, Beck Depression Inventory, Affective Pain Rating Index of the Short-Form McGill Pain Questionnaire). Fourteen serious adverse events were recorded and resolved. INTERPRETATION: VS/ALIC DBS to modulate the affective sphere of pain represents a paradigm shift in chronic pain management. Although this exploratory study was negative for its primary endpoint, VS/ALIC DBS demonstrated an acceptable safety profile and statistically significant improvements on multiple outcome measures related to the affective sphere of pain. Therefore, we believe these results justify further work on neuromodulation therapies targeting the affective sphere of pain. Ann Neurol 2017;81:653-663.

Preserving cortico-striatal function: deep brain stimulation in Huntington's disease.

Huntington's disease (HD) is an incurable neurodegenerative disease characterized by the triad of chorea, cognitive dysfunction and psychiatric disturbances. Since the discovery of the HD gene, the pathogenesis has been outlined, but to date a cure has not been found. Disease modifying therapies are needed desperately to improve function, alleviate suffering, and provide hope for symptomatic patients. Deep brain stimulation (DBS), a proven therapy for managing the symptoms of some neurodegenerative movement disorders, including Parkinson's disease, has been reported as a palliative treatment in select cases of HD with debilitating chorea with variable success. New insights into the mechanism of action of DBS suggest it may have the potential to circumvent other manifestations of HD including cognitive deterioration. Furthermore, because DBS is already widely used, reversible, and has a risk profile that is relatively low, new studies can be initiated. In this article we contend that new clinical trials be considered to test the effects of DBS for HD.

A Randomized Sham-Controlled Trial of Deep Brain Stimulation of the Ventral Capsule/Ventral Striatum for Chronic Treatment-Resistant Depression.

BACKGROUND: Multiple open-label trials of deep brain stimulation (DBS) for treatment-resistant depression (TRD), including those targeting the ventral capsule/ventral striatum target, have shown encouraging response rates. However, no randomized controlled trials of DBS for TRD have been published. METHODS: Thirty patients with TRD participated in a sham-controlled trial of DBS at the ventral capsule/ventral striatum target for TRD. Patients were randomized to active versus sham DBS treatment in a blinded fashion for 16 weeks, followed by an open-label continuation phase. The primary outcome measure was response, defined as a 50% or greater improvement on the Montgomery-Åsberg Depression Rating Scale from baseline. RESULTS: There was no significant difference in response rates between the active (3 of 15 subjects; 20%) and control (2 of 14 subjects; 14.3%) treatment arms and no significant difference between change in Montgomery-Åsberg Depression Rating Scale scores as a continuous measure upon completion of the 16-week controlled phase of the trial. The response rates at 12, 18, and 24 months during the open-label continuation phase were 20%, 26.7%, and 23.3%, respectively. CONCLUSION: The results of this first randomized controlled study of DBS for the treatment of TRD did not demonstrate a significant difference in response rates between the active and control groups at the end of the 16-week controlled phase. However, a range of 20% to 26.7% of patients did achieve response at any time during the open-label continuation phase. Future studies, perhaps utilizing alternative study designs and stimulation parameters, are needed.

Impact of mild cognitive impairment on outcome following deep brain stimulation surgery for Parkinson's disease.

INTRODUCTION: Unlike dementia, the effect of mild cognitive impairment (MCI) on outcomes after deep brain stimulation (DBS) in Parkinson's disease (PD) is less clear. We aimed to examine the effect of MCI on short- and long-term DBS outcomes. METHODS: To study the effect of MCI type, cognitive domains (attention, language, visuospatial, memory, executive function), and Dementia Rating Scale (DRS) score on immediate postoperative outcomes (postoperative confusion, hospitalization days), PD patients who underwent DBS at our Center from 2006 to 2011 were analyzed. To determine cognitive predictors of intermediate (6-month) and long-term (1-year) post-operative outcomes, the changes in functional and quality-of-life (QOL) scores were analyzed in a smaller group with available preoperative health status measures. RESULTS: We identified 130 patients [71% male, mean age: 63 ± 9.1, mean PD duration: 10.7 ± 5.1]. At preoperative assessment, 60% of patients had multiple-domain MCI, 21% had single-domain MCI, and 19% had normal cognition. MCI presence and type as well as DRS performance did not affect immediate outcomes. Attention impairment predicted longer postoperative hospitalization (P = 0.0015) and showed a trend towards occurrence of postoperative confusion (P = 0.089). For intermediate and long-term outcomes we identified 56 patients [73.2% male, mean age: 61.3 ± 9.6, mean PD duration: 10.6 ± 4.7]. Visuospatial impairment showed a trend towards less improvement in 6-month functional score (P = 0.0652), and 1-year QOL score (P = 0.0517). CONCLUSION: The presence of MCI did not affect DBS outcomes. However, the types of impaired domains were more detrimental. Detailed cognitive testing can help stratify low- and high-risk patients based on their pattern of cognitive dysfunction.

Comprehensive, Multidisciplinary Deep Brain Stimulation Screening for Parkinson Patients: No Room for "Short Cuts".

Careful, often cumbersome, screening is a fundamental part of DBS evaluation in Parkinson's disease (PD). It often involves a brain MRI, neuropsychological testing, neurological, surgical, and psychiatric evaluation, and "ON/OFF" motor testing. Given that DBS has now been a standard treatment for advanced PD, with clinicians' improved comfort and confidence in screening and referring patients for DBS, we wondered whether we can now streamline our lengthy evaluation process. We reviewed all PD patients evaluated for DBS at our center between 2006 and 2011 and analyzed the reasons for exclusion and for dropping out despite passing the screening process. A total of 223 PD patients who underwent DBS evaluation had complete charting. Only 131 (58.7%) patients were successfully implanted. Sixty-one (27.3%) patients were excluded after screening because of significant cognitive decline (32.7%), early disease with room for medication adjustment (29.5%), behavioral dysfunction (21.3%), suspected secondary parkinsonism or atypical parkinsonism syndrome (13.1%), PD, but with poor levodopa response (11.4%), unrealistic goals (9.8%), PD with predominant axial symptoms (6.5%), significant comorbidities (6.5%), or abnormal brain imaging (3.2%). In addition, 31 (13.9%) patients were cleared for surgery, but either chose not have it (18 patients), were lost to follow-up (12 patients), or were denied by medical insurance (1 patient). Through careful screening, a significant percentage of surgical candidates continue to be identified as less suitable because of a variety of reasons. This underscores the continued need for a comprehensive, multidisciplinary screening process.

Where in the brain is depression?

Major depressive disorder is a serious medical illness which is responsible for considerable morbidity and disability. Despite decades of research, the neural basis for depression is still incompletely understood. In this review, evidence from neuroimaging, neuropsychiatric and brain stimulations studies are explored to answer the question regarding the localization of depression in the brain. Neuroimaging studies indicate that although many regions of the brain have been repeatedly implicated in the pathophysiology of depression, not many consistent findings have been found until present. In recent times, the focus of neuroimaging has shifted from regional brain abnormalities to circuit level connectivity abnormalities. However, connectivity models are inherently more complicated, and the validity of these models remains to be tested. Neuropsychiatric studies of illnesses such as Parkinson's disease and stroke provide promising clues regarding areas involved in depression, but again consistent findings are rare. Similarly, stimulation of a variety of brain regions and circuits has been reported as being effective in depression. Therefore, the current knowledge indicates that the pathophysiology of depression may be distributed across many brain regions and circuits. In future studies, this distributed nature of depression needs to be further investigated, primary and secondary areas affected need to be identified, and new paradigms to explain complex mental functions need to be explored.

Parkinson disease: not just a movement disorder.

Nonmotor symptoms are common in Parkinson disease and can significantly worsen the health and quality of life of the patient and family members. These symptoms can be broadly categorized as sensory, autonomic, cognitive-behavioral, and sleep-related. Clinicians can improve the care of these patients by recognizing and addressing these problems.

Electroconvulsive therapy: what the internist needs to know.

Although electroconvulsive therapy (ECT) is widely used to treat a number of psychiatric disorders, many physicians are still unfamiliar with the procedure, its indications, and its contraindications. This article is an internist's guide to ECT, with particular focus on how commonly prescribed medications and medical conditions affect ECT.

Versatile platform for creating gradient combinatorial libraries via modulated light exposure.

This article details the design, construction, and operation of flexible system that modulates light exposure for the purpose of fabricating continuous and discrete gradient combinatorial libraries. Designed for versatility, the device combines "off the shelf" components, modular accessories, and flexible computer control, so that it can be used for a variety of combinatorial research applications. Salient aspects and capabilities of the instrument are illustrated through two practical examples. The first case demonstrates how user defined exposure functions can be used to create continuous surface energy gradient libraries with a linear profile. The second example illustrates the creation of continuous and discrete libraries for mapping exposure-property functions in a photocurable polymer system.

A malignant neuroleptic spectrum: review of diagnostic criteria and treatment implications in three case reports.

Prompt identification of cases of Neuroleptic Malignant Syndrome (NMS) pose a diagnostic and treatment challenge. Three hospital cases of neuroleptic toxicity were reviewed and compared across five published diagnostic criteria sets for NMS. Of these criteria sets, only Levenson's criteria led to the detection of NMS in two out of our three patients. This criteria set supports a NMS spectrum concept, allowing earlier diagnosis and intervention. Lorazepam was used as initial treatment, which provided significant improvement. Use of Levenson's criteria for early diagnosis of NMS and lorazepam for its treatment may be useful tools for the early management of NMS.